© 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. 12843
    Prev
    Next
    INDEX
    Explanations

    news reports about law enforcement and military incidents

    oai_token-act-pair · gemini-2.0-flash

    death and pursuit

    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
    GraphicsUnit
    -0.79
    writeFieldEnd
    -0.77
    LookAnd
    -0.67
    AndEndTag
    -0.66
    ConstraintMaker
    -0.65
    SharedCtor
    -0.64
     ModelRenderer
    -0.64
    SourceChecksum
    -0.63
    setVerticalGroup
    -0.63
     MenuView
    -0.62
    POSITIVE LOGITS
    Còn
    0.41
     thuê
    0.40
     ")";
    0.38
     group
    0.38
    begingroup
    0.37
     "]";
    0.37
    فيه
    0.37
    éroport
    0.37
    omos
    0.37
    outgoing
    0.36
    Activations Density 0.537%

    No Known Activations