© 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. 214881
    Prev
    Next
    INDEX
    Explanations

    repository interfaces

    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
     AudioClip
    0.35
     regularity
    0.34
     bounding
    0.34
     baseHP
    0.34
    bounding
    0.34
    ሚ
    0.33
     texte
    0.33
    laughs
    0.33
     Verständnis
    0.33
    厥
    0.33
    POSITIVE LOGITS
     shaved
    0.41
    ത്തക
    0.40
     পিলার
    0.38
     led
    0.37
    Preferences
    0.37
     invaded
    0.37
    COLUMN
    0.37
    Slider
    0.37
    Map
    0.37
     shaving
    0.37
    Activations Density 0.000%

    No Known Activations