© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6984
    Prev
    Next
    INDEX
    Explanations

    the "sc" prefix, likely looking for variants of "scam"

    oai_token-act-pair · gemini-2.0-flash

    sc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    anız
    -0.49
    strat
    -0.48
    kháu
    -0.47
     StringTokenizer
    -0.47
    новниш
    -0.47
    InputBorder
    -0.46
    em
    -0.46
     Fitzgerald
    -0.45
     maille
    -0.45
    lasser
    -0.45
    POSITIVE LOGITS
    indrome
    0.59
    orsese
    0.52
    urlpatterns
    0.50
    arily
    0.50
    utdown
    0.49
    ratic
    0.49
    rature
    0.48
    ariously
    0.47
    DataAnnotations
    0.47
    rawl
    0.47
    Activations Density 7.916%

    No Known Activations