© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47215
    Prev
    Next
    INDEX
    Explanations

    without being

    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_3_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
    ви
    0.92
    ли
    0.89
    í
    0.76
     vermek
    0.75
    λη
    0.74
    يد
    0.73
    يش
    0.73
    т
    0.73
    ро
    0.73
    их
    0.71
    POSITIVE LOGITS
    EL
    0.72
    is
    0.71
    was
    0.66
    的游戏
    0.66
    No
    0.63
    TE
    0.63
    Max
    0.63
    has
    0.58
    et
    0.58
     व
    0.57
    Activations Density 0.111%

    No Known Activations