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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1268
    Prev
    Next
    INDEX
    Explanations

    citations in the formats `>` and `]`

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    MigrationBuilder
    -1.09
    Geplaatst
    -1.05
     Roskov
    -1.05
    )++;
    -1.02
     &___
    -0.96
    LookAnd
    -0.95
    GraphicsUnit
    -0.94
    '][]
    -0.94
    ,:);
    -0.93
    InvalidProtocol
    -0.91
    POSITIVE LOGITS
    ,
    0.69
    .
    0.55
    ঙ্গ
    0.45
    :
    0.44
    ftc
    0.44
     Welle
    0.41
    ;
    0.39
     den
    0.38
    чах
    0.38
    inoco
    0.38
    Activations Density 1.948%

    No Known Activations