© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61367
    Prev
    Next
    INDEX
    Explanations

    1

    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_59_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
    あれば
    0.52
    あって
    0.49
    出
    0.47
    ியுள்ளது
    0.47
    出て
    0.47
    ியது
    0.46
    ありますが
    0.42
    জনক
    0.39
    出演
    0.39
    മില്ല
    0.39
    POSITIVE LOGITS
    <0xC2>
    0.37
     …………
    0.35
     ↑
    0.35
    وپ
    0.34
     ‎
    0.33
    ξ
    0.33
    ౌ
    0.33
    ↗
    0.33
    >,</
    0.33
    деть
    0.32
    Activations Density 0.003%

    No Known Activations