Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14491
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental and legal procedures

    oai_token-act-pair · gemini-2.0-flash

    Formal or Political texts

    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
    ButterKnife
    -0.57
     defStyleAttr
    -0.54
    الإنجليزية
    -0.53
    +#+#
    -0.50
     UITableViewCell
    -0.50
    HtmlAttribute
    -0.50
    matchCondition
    -0.49
    dega
    -0.48
    CrossRef
    -0.48
    trane
    -0.48
    POSITIVE LOGITS
    transQ
    0.73
    uxxxx
    0.63
     ویکی‌پدی
    0.58
    bleshooting
    0.56
    RectangleBorder
    0.54
    prefixer
    0.52
    Jeografia
    0.51
     незавершена
    0.49
     szóci
    0.49
    wness
    0.48
    Activations Density 0.153%

    No Known Activations