© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14350
    Prev
    Next
    INDEX
    Explanations

    words related to police investigations and illegal activities

    oai_token-act-pair · gemini-2.0-flash

    reports

    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
    several
    -0.92
     three
    -0.89
     Several
    -0.88
    Several
    -0.87
    ReusableCell
    -0.86
     several
    -0.85
    two
    -0.84
     two
    -0.84
     Three
    -0.83
    trois
    -0.82
    POSITIVE LOGITS
     over
    0.86
    Over
    0.73
    over
    0.69
     Over
    0.68
     OVER
    0.62
    Hochspringen
    0.55
    overs
    0.52
     över
    0.51
     sobre
    0.50
     @}
    0.47
    Activations Density 29.900%

    No Known Activations