© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83701
    Prev
    Next
    INDEX
    Explanations

    code dependencies

    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_23_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
     Π
    0.42
     lecithin
    0.39
     reprieve
    0.38
     □
    0.37
     monologue
    0.37
     অথচ
    0.36
     breve
    0.36
     convertView
    0.35
    쯤
    0.35
     مختصر
    0.35
    POSITIVE LOGITS
     используются
    0.43
    öö
    0.42
    ប្រើ
    0.42
     использованием
    0.42
     పరిశ
    0.41
     інших
    0.40
     сложные
    0.40
     சேர்க்க
    0.40
    ży
    0.39
     использование
    0.39
    Activations Density 0.000%

    No Known Activations