© 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. 127943
    Prev
    Next
    INDEX
    Explanations

    diatomaceous earth

    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
    ла
    0.75
    ia
    0.65
    ieu
    0.63
    ョン
    0.57
    ية
    0.56
    3
    0.56
    BatchNorm
    0.55
    IAT
    0.55
    -}$
    0.54
    ieg
    0.53
    POSITIVE LOGITS
    ال
    0.85
    که
    0.84
    '
    0.76
    م
    0.73
     It
    0.70
    它
    0.70
     it
    0.68
    れ
    0.67
    க்
    0.66
    speople
    0.66
    Activations Density 0.000%

    No Known Activations