© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206298
    Prev
    Next
    INDEX
    Explanations

    mani, dan, ani, Idri

    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_10_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
    な
    0.79
    тива
    0.74
    ups
    0.69
    க
    0.69
     carcinomas
    0.68
    Π
    0.68
    க்கண
    0.66
    kers
    0.65
    Г
    0.64
    gher
    0.63
    POSITIVE LOGITS
     LAW
    0.72
     pł
    0.70
     "//
    0.70
     könne
    0.69
     ó
    0.68
     İl
    0.66
     '//
    0.66
     deutlich
    0.65
     PAUL
    0.65
     ö
    0.64
    Activations Density 0.000%

    No Known Activations