© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133647
    Prev
    Next
    INDEX
    Explanations

    setup.py or function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    1
    1.20
    a
    1.15
    ه
    1.09
    া
    1.01
    ub
    0.94
    ters
    0.94
    上
    0.93
    </h3>
    0.93
    ان
    0.93
    ract
    0.93
    POSITIVE LOGITS
    ו
    1.43
    ל
    1.06
    ம்
    1.05
     sẽ
    1.02
    も
    1.02
    ം
    0.91
     ຊ
    0.88
    ס
    0.88
    ం
    0.88
     poate
    0.87
    Activations Density 0.000%

    No Known Activations