© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9849
    Prev
    Next
    INDEX
    Explanations

    words related to scientific writing and publishing with emphasis on collaboration, results, properties and related changes

    oai_token-act-pair · gemini-2.0-flash

    descriptive nouns related to characteristics and patterns

    np_token-act-pair-logits · gpt-4o-mini

    Describes behavior

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.68
    GraphicsUnit
    -0.68
    //</
    -0.50
    tonode
    -0.49
    AnimationsModule
    -0.48
    ريكية
    -0.48
     betweenstory
    -0.47
    >-->
    -0.46
     Cientí
    -0.46
    الإنجليزية
    -0.46
    POSITIVE LOGITS
     characteristics
    1.09
     behaviour
    1.05
     configuration
    1.02
     behavior
    1.02
     pattern
    1.02
     style
    1.02
     patterns
    1.00
     styles
    0.98
     habits
    0.95
    characteristics
    0.92
    Activations Density 7.499%

    No Known Activations