© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8443
    Prev
    Next
    INDEX
    Explanations

    words related to legal events and criminal accusations.

    oai_token-act-pair · gemini-2.0-flash

    crime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ſhe
    -0.70
     tranſ
    -0.69
     Monfieur
    -0.67
     Efq
    -0.66
     leſs
    -0.65
     ब्रेकडाउन
    -0.64
     myſelf
    -0.64
     ſta
    -0.63
    <_>
    -0.62
     itſelf
    -0.62
    POSITIVE LOGITS
     ComVisible
    0.84
     police
    0.65
    RenderAtEndOf
    0.63
     RCMP
    0.58
    Police
    0.58
    جغرافيا
    0.56
    ggiata
    0.56
     homicide
    0.56
    FundMe
    0.56
    SharedDtor
    0.55
    Activations Density 2.824%

    No Known Activations