© 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. 9001
    Prev
    Next
    INDEX
    Explanations

    words associated with mystical power and the human body, particularly in a context of conflict or judgment.

    oai_token-act-pair · gemini-2.0-flash

    technical papers

    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
    onAttach
    -0.58
     FixedUpdate
    -0.52
    CIC
    -0.52
    WriteLiteral
    -0.50
    <>();
    -0.50
    sequelize
    -0.49
     CIC
    -0.49
    IGATION
    -0.48
    ibly
    -0.47
    fxml
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.64
    RenderAtEndOf
    0.63
    Insee
    0.63
    GEBURTSDATUM
    0.59
    unicaciones
    0.58
    INSEE
    0.57
     utafiti
    0.57
     kaarangay
    0.57
     Reisedaten
    0.57
    पया
    0.56
    Activations Density 2.747%

    No Known Activations