© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2399
    Prev
    Next
    INDEX
    Explanations

    words associated with celebrations, holidays, and costumes

    oai_token-act-pair · gemini-2.0-flash

    Halloween costumes

    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
     '\\;'
    -0.56
    ">:
    -0.48
    Deacti
    -0.48
    seras
    -0.47
     contextLoads
    -0.45
     ThemeData
    -0.45
    yntaxException
    -0.45
     pronti
    -0.45
    remmo
    -0.45
     للاسماء
    -0.43
    POSITIVE LOGITS
     насељу
    0.59
    modb
    0.56
    <bos>
    0.54
     sats
    0.50
     vz
    0.49
     Vichy
    0.48
    RepeatedField
    0.48
    מט
    0.48
    δω
    0.48
    migrationBuilder
    0.47
    Activations Density 0.581%

    No Known Activations