© 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. 9608
    Prev
    Next
    INDEX
    Explanations

    a disparate collection of words and word fragments from various European languages, code, and medical terminology, with no clear unifying theme

    oai_token-act-pair · gemini-2.0-flash

    code fragments

    np_max-act · 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
     CanadaChoose
    -0.57
     Référence
    -0.55
    grà
    -0.52
    modb
    -0.50
    Hentet
    -0.50
    aver
    -0.49
    rettet
    -0.49
     ModelExpression
    -0.48
    lesi
    -0.47
    хва
    -0.47
    POSITIVE LOGITS
    Попис
    0.65
    DebuggerNonUser
    0.64
    basicConfig
    0.61
     NSCoder
    0.59
    Демографія
    0.56
     ProtoMessage
    0.56
     Wiktionnaire
    0.56
    latego
    0.55
    resave
    0.55
     uLocal
    0.53
    Activations Density 10.882%

    No Known Activations