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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6629
    Prev
    Next
    INDEX
    Explanations

    historical facts, specifically involving political events, treaties, and people

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terms

    np_token-act-pair-logits · gpt-4o-mini
    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
     חיצוניים
    -0.76
    TargetException
    -0.73
     vectorielles
    -0.72
    )?;
    -0.69
     تانيه
    -0.65
     estimés
    -0.64
     refroid
    -0.63
     mourir
    -0.62
     känna
    -0.60
     présentes
    -0.60
    POSITIVE LOGITS
    MigrationBuilder
    0.55
    jiri
    0.48
    didSet
    0.47
     may
    0.45
    AccessorTable
    0.44
    Див
    0.44
    enance
    0.43
     nakalista
    0.43
    PerformLayout
    0.43
    InputLabel
    0.43
    Activations Density 2.348%

    No Known Activations