© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4114
    Prev
    Next
    INDEX
    Explanations

    things like "cat", "ful" and computer code dividers

    oai_token-act-pair · gemini-2.0-flash

    ful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ‘
    -0.61
     '
    -0.58
     
    -0.58
    .
    -0.54
    !
    -0.51
     “
    -0.49
    /
    -0.47
    ↵↵
    -0.47
     (
    -0.47
     C
    -0.46
    POSITIVE LOGITS
    //
    1.16
     itſelf
    0.97
    parsedMessage
    0.97
    RTLD
    0.94
     ModelExpression
    0.90
    حياتها
    0.88
    styleType
    0.87
     myſelf
    0.87
     للمعارف
    0.87
    הערות
    0.87
    Activations Density 0.228%

    No Known Activations