© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8220
    Prev
    Next
    INDEX
    Explanations

    scene breaks, titles, and chapter beginnings

    oai_token-act-pair · gemini-2.0-flash

    fanfiction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AndEndTag
    -0.82
    MLLoader
    -0.81
     nakalista
    -0.77
    IntoConstraints
    -0.76
     متعلقه
    -0.74
     TextInputType
    -0.73
     يتيمه
    -0.72
    LayoutConstraint
    -0.72
    errHandler
    -0.71
    脚注の使い方
    -0.70
    POSITIVE LOGITS
    Personensuche
    0.46
    lence
    0.41
     "
    0.41
     “
    0.40
    残
    0.39
    till
    0.39
    フラン
    0.38
    OData
    0.38
     papà
    0.38
    ål
    0.37
    Activations Density 2.056%

    No Known Activations