© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9591
    Prev
    Next
    INDEX
    Explanations

    code snippets about quizzes and camps and legal testimonies about agents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -3.25
    '
    -0.77
    The
    -0.63
    ’
    -0.63
     the
    -0.61
    <h2>
    -0.52
    #
    -0.52
    Con
    -0.49
    It
    -0.49
    By
    -0.48
    POSITIVE LOGITS
    orative
    0.57
    ophone
    0.55
    disambiguation
    0.53
    minist
    0.53
     Strap
    0.52
    xffffffff
    0.52
     مشين
    0.51
    λαν
    0.51
    kapital
    0.51
     Tent
    0.50
    Activations Density 4.849%

    No Known Activations