© 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-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93584
    Prev
    Next
    INDEX
    Explanations

    make

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itih
    0.35
    ㏄
    0.34
    (`.
    0.32
    typeName
    0.31
    -;
    0.31
    íu
    0.31
    -_-
    0.30
    )}>
    0.30
    )-,
    0.30
    getFocusAreas
    0.30
    POSITIVE LOGITS
     use
    2.38
    use
    2.08
     Use
    1.97
    Use
    1.92
     gebruik
    1.52
     USE
    1.45
    USE
    1.41
     использование
    1.34
     استفاده
    1.33
     uso
    1.30
    Activations Density 0.008%

    No Known Activations