© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9164
    Prev
    Next
    INDEX
    Explanations

    legal citations using "Id." and page numbers, with some recognition of "at" and digits.

    oai_token-act-pair · gemini-2.0-flash

    Legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    SerializedSize
    -0.70
    NewUrlParser
    -0.69
    VersionUID
    -0.68
    AlterField
    -0.68
    CompleteListener
    -0.67
    GTCX
    -0.62
    Hochspringen
    -0.62
    ABAD
    -0.60
    ScopeManager
    -0.60
    SuccessListener
    -0.60
    POSITIVE LOGITS
     cat
    0.47
    cat
    0.46
     Cat
    0.45
    rzost
    0.44
    lect
    0.41
    </sup>
    0.40
     peix
    0.40
    Cat
    0.40
    getList
    0.40
    rat
    0.38
    Activations Density 2.712%

    No Known Activations