© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    words related to crime, punishment, and/or strongly negative opinions

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    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
     Muslim
    -1.83
     Islamic
    -1.70
     Islam
    -1.63
     Muslims
    -1.57
    Muslim
    -1.50
    Islamic
    -1.48
     Moslem
    -1.47
     muslim
    -1.46
    Islam
    -1.44
     Mohammed
    -1.35
    POSITIVE LOGITS
    eltjes
    0.49
    HtmlAttribute
    0.49
     createState
    0.49
    _();
    0.47
    <bos>
    0.47
    ViewImports
    0.43
     lauter
    0.42
    Parcelize
    0.40
    ObjectContext
    0.39
    createStatement
    0.38
    Activations Density 0.564%

    No Known Activations