© 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. 7873
    Prev
    Next
    INDEX
    Explanations

    file names and common coding extensions

    oai_token-act-pair · gemini-2.0-flash

    code snippets and programming elements

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

    file extensions

    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
     B
    -0.52
     .
    -0.50
     N
    -0.48
     you
    -0.47
     Be
    -0.46
     members
    -0.46
    name
    -0.46
     BY
    -0.46
     has
    -0.45
     us
    -0.45
    POSITIVE LOGITS
     ModelExpression
    1.00
    AndEndTag
    0.97
    mybatisplus
    0.91
    évaluateur
    0.91
     Efq
    0.88
    StoryboardSegue
    0.85
     Jefus
    0.85
    WriteBarrier
    0.84
    MigrationBuilder
    0.84
    WebVitals
    0.83
    Activations Density 1.737%

    No Known Activations