© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4222
    Prev
    Next
    INDEX
    Explanations

    mentions of crime, conflict and legal actions

    oai_token-act-pair · 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
    LookAnd
    -0.89
    indd
    -0.67
     '\\;'
    -0.66
     ProtoMessage
    -0.65
     للمعارف
    -0.62
     ImGui
    -0.57
    횟
    -0.57
     незавершена
    -0.56
    WriteLiteral
    -0.56
    ruik
    -0.56
    POSITIVE LOGITS
     snippetHide
    0.60
    qrstuvwxyz
    0.57
    ViewFeatures
    0.54
    nought
    0.54
    JAMIN
    0.52
    MemoryWarning
    0.51
    Bronnen
    0.50
    aconda
    0.49
    لمانيا
    0.47
    BASELINE
    0.47
    Activations Density 5.719%

    No Known Activations