© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8681
    Prev
    Next
    INDEX
    Explanations

    construction and action

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <0x0D>
    0.73
    ส
    0.73
    I
    0.61
    О
    0.61
    ای
    0.60
    EN
    0.59
    З
    0.59
    Food
    0.58
    ↵↵
    0.58
    –
    0.58
    POSITIVE LOGITS
     செயற்ப
    0.56
    porters
    0.53
     செயல்ப
    0.53
    volvimento
    0.52
     mellem
    0.51
     преимущества
    0.51
     अरो
    0.51
     Warsz
    0.49
     между
    0.49
     між
    0.49
    Activations Density 0.070%

    No Known Activations