© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18138
    Prev
    Next
    INDEX
    Explanations

    glasses and prescription

    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_15_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
    --
    0.53
     Tiere
    0.50
     Aman
    0.49
     Pinterest
    0.49
     plush
    0.48
     –
    0.47
    <h3>
    0.46
     Berth
    0.46
    itudinal
    0.45
     Bulletin
    0.45
    POSITIVE LOGITS
    、$
    0.60
    溶液
    0.55
    <0xCF>
    0.53
     سے
    0.52
     financiación
    0.52
    から
    0.51
    oarece
    0.51
    𝚍
    0.51
     من
    0.51
     ඉතා
    0.51
    Activations Density 0.003%

    No Known Activations