© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10633
    Prev
    Next
    INDEX
    Explanations

    years, locations and events

    oai_token-act-pair · gemini-2.0-flash

    wikipedia articles

    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
     kasarigan
    -0.49
     SafeMath
    -0.47
    Tembelea
    -0.45
    FileDescriptor
    -0.44
     abraço
    -0.44
    المكان
    -0.44
    ForValue
    -0.43
    йки
    -0.43
     ANGELES
    -0.43
     Differenz
    -0.43
    POSITIVE LOGITS
     كومونز
    0.64
    XtraReports
    0.61
    </thead>
    0.61
     الحره
    0.57
     الاطلاع
    0.56
     unknownFields
    0.55
     initComponents
    0.52
     arşivlendi
    0.51
     Hinsicht
    0.50
    fault
    0.50
    Activations Density 2.828%

    No Known Activations