© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3812
    Prev
    Next
    INDEX
    Explanations

    mentions of official reports or reporting

    oai_token-act-pair · gemini-2.0-flash

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Reports
    -1.22
     Report
    -1.18
     reports
    -1.18
     report
    -1.18
     reporting
    -1.17
    reports
    -1.16
    Report
    -1.13
     REPORTS
    -1.11
     REPORT
    -1.10
    report
    -1.09
    POSITIVE LOGITS
    :✨
    0.77
    setVerticalGroup
    0.63
    PYX
    0.58
     <=",
    0.54
     оригіналу
    0.54
    MigrationBuilder
    0.52
    GEBURTSDATUM
    0.50
    WebMethod
    0.49
    mentaux
    0.47
    oredCriteria
    0.47
    Activations Density 35.505%

    No Known Activations