© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16032
    Prev
    Next
    INDEX
    Explanations

    words related to drilling and boring holes, and/or the passive voice

    oai_token-act-pair · gemini-2.0-flash

    tool or surgery processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GEBURTSDATUM
    -0.88
    ⓧ
    -0.85
     ModelExpression
    -0.82
     ویکی‌پدیا
    -0.80
     AssemblyProduct
    -0.80
    PYX
    -0.79
     StatelessWidget
    -0.79
    EndGlobalSection
    -0.78
    Autoritní
    -0.75
    المناصب
    -0.73
    POSITIVE LOGITS
     lowered
    0.52
    lower
    0.46
    liferay
    0.40
     lowering
    0.40
     di
    0.40
    Attach
    0.40
    Lower
    0.40
    pierw
    0.39
     lower
    0.39
     uns
    0.39
    Activations Density 2.104%

    No Known Activations