© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3300
    Prev
    Next
    INDEX
    Explanations

    words related to religion, disease/death, and/or agriculture and harvest

    oai_token-act-pair · gemini-2.0-flash

    divine retribution/consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AndEndTag
    -0.72
     مرئيه
    -0.68
     ostavi
    -0.66
     Vikipedi
    -0.66
    ","");
    -0.63
    DockStyle
    -0.61
     gainera
    -0.60
    lidae
    -0.59
     GeoNames
    -0.59
    日閲覧
    -0.58
    POSITIVE LOGITS
    Condol
    0.57
    fvar
    0.47
    DataAnnotations
    0.43
    новниш
    0.42
    來說
    0.41
     Dem
    0.41
    IsMutable
    0.39
     attacc
    0.39
     adverse
    0.39
     attack
    0.38
    Activations Density 1.732%

    No Known Activations