© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13299
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and business documents, especially those indicating forward-looking statements, copyright, or disclaimers.

    oai_token-act-pair · gemini-2.0-flash

    code and legal statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     متعلقه
    -0.82
     greateſt
    -0.76
     ſeveral
    -0.73
     pleaſure
    -0.72
    expandindo
    -0.72
     purpoſe
    -0.69
     المعيارى
    -0.69
     مشين
    -0.69
    存于互联网档案馆
    -0.68
     beſt
    -0.67
    POSITIVE LOGITS
    <bos>
    2.02
    <eos>
    0.48
     the
    0.48
     to
    0.45
    тся
    0.42
    ungs
    0.41
     it
    0.40
    щаться
    0.40
    ung
    0.40
     that
    0.40
    Activations Density 4.809%

    No Known Activations