© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10157
    Prev
    Next
    INDEX
    Explanations

    a mix of capitalized words, particularly proper nouns and some medical terms, although the function is not very clear overall.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    对
    -0.54
    .
    -0.51
     scopo
    -0.48
    ,
    -0.46
    gap
    -0.46
    對
    -0.45
    !
    -0.44
    ث
    -0.43
    ic
    -0.43
    son
    -0.42
    POSITIVE LOGITS
    enumi
    0.93
    providedIn
    0.85
    mybatisplus
    0.82
    Chham
    0.82
    enumii
    0.80
    enterOuterAlt
    0.79
     nakalista
    0.78
    DockStyle
    0.77
    ^(@)
    0.74
     فريبيس
    0.73
    Activations Density 9.742%

    No Known Activations