© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 37014
    Prev
    Next
    INDEX
    Explanations

    syntax for code blocks

    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_31_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
    ،
    0.43
     ،
    0.40
    Ｏ
    0.37
    ，
    0.37
     p
    0.36
    Report
    0.36
    without
    0.36
    Without
    0.36
    Advance
    0.36
    Нет
    0.36
    POSITIVE LOGITS
     पृथ्वी
    0.37
     கடுமையான
    0.36
    婜
    0.36
    யில்
    0.36
     Seine
    0.36
    เฟ
    0.36
    >\<^
    0.36
     зем
    0.36
    Configs
    0.36
     homeomorphism
    0.36
    Activations Density 0.054%

    No Known Activations