© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12979
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and the phrase "collect the terms".

    oai_token-act-pair · gemini-2.0-flash

    terms

    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
     GenerationType
    -0.78
     Paglinawan
    -0.75
    contentLoaded
    -0.75
     snippetHide
    -0.73
     betweenstory
    -0.72
    ⓧ
    -0.68
    astéroïdes
    -0.67
    GraphicsUnit
    -0.64
    memoized
    -0.64
    archiviato
    -0.63
    POSITIVE LOGITS
     ontem
    0.38
    orce
    0.37
    BagLayout
    0.36
    GEBURTSDATUM
    0.35
     tháng
    0.35
     depends
    0.35
     Nol
    0.34
     oseb
    0.34
    Minus
    0.34
    NSIndexPath
    0.33
    Activations Density 1.717%

    No Known Activations