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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1274
    Prev
    Next
    INDEX
    Explanations

    text from professional biographies and resumes

    oai_token-act-pair · gemini-2.0-flash

    Educational institutions

    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
    basicConfig
    -0.66
    BUSINESS
    -0.63
     BUSINESS
    -0.62
     business
    -0.60
    ReusableCell
    -0.59
     Business
    -0.57
    RenderAtEndOf
    -0.56
    Business
    -0.55
    business
    -0.54
    NOST
    -0.51
    POSITIVE LOGITS
    出版年
    0.72
     Direktur
    0.52
    はじめに
    0.47
     gomma
    0.47
    $_['
    0.46
    spół
    0.45
    جغرافيا
    0.44
     "/";
    0.43
    calciatore
    0.43
    èvement
    0.43
    Activations Density 7.836%

    No Known Activations