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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4328
    Prev
    Next
    INDEX
    Explanations

    words related to scientific, technical, or foreign language contexts

    oai_token-act-pair · gemini-2.0-flash

    technical writings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Hozzáférés
    -0.50
    teryx
    -0.47
    MEM
    -0.47
     مشين
    -0.46
     zip
    -0.46
    IntoConstraints
    -0.46
    writeFile
    -0.46
     MEM
    -0.44
    عل
    -0.44
    kungen
    -0.43
    POSITIVE LOGITS
    URLException
    0.75
    MessageOf
    0.73
    findpost
    0.69
     Audiodateien
    0.66
    amaño
    0.65
     ModelExpression
    0.65
     AssemblyCompany
    0.62
     HasFactory
    0.60
     raiſ
    0.60
     siyang
    0.59
    Activations Density 20.164%

    No Known Activations