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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16296
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conflict, politics, and social issues

    oai_token-act-pair · gemini-2.0-flash

    sickness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Normdatei
    -0.56
     Signalez
    -0.54
    __);
    -0.51
    myra
    -0.50
     appelez
    -0.50
     puntual
    -0.49
    ToDate
    -0.48
    archiviato
    -0.45
    ﷺ
    -0.45
     viết
    -0.45
    POSITIVE LOGITS
     disease
    0.97
    disease
    0.88
     Disease
    0.78
     DISEASE
    0.77
     sickness
    0.73
     crime
    0.73
    Disease
    0.73
     illness
    0.72
     disorder
    0.70
     Sünde
    0.68
    Activations Density 2.892%

    No Known Activations