© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2552
    Prev
    Next
    INDEX
    Explanations

    information about a person from a biography, resume, or similar document, especially looking for "He" or "She".

    oai_token-act-pair · gemini-2.0-flash

    biographies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     protoimpl
    -0.55
    OGND
    -0.52
    urlpatterns
    -0.52
    ngdoc
    -0.50
     xv
    -0.50
    ToAction
    -0.50
    UserScript
    -0.49
    parsedMessage
    -0.49
     חיצוניים
    -0.49
     DBNull
    -0.48
    POSITIVE LOGITS
    RenderAtEndOf
    0.62
     précision
    0.56
     Beauchamp
    0.54
    jsko
    0.52
    jednoc
    0.52
     Désolé
    0.51
    AccessFile
    0.49
    钥
    0.49
     împre
    0.49
     spreken
    0.48
    Activations Density 2.283%

    No Known Activations