© 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. 39835
    Prev
    Next
    INDEX
    Explanations

    ML formatting

    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
    ین
    0.86
    ב
    0.85
    ید
    0.77
    ک
    0.77
     obscured
    0.74
     snapped
    0.73
     imbued
    0.71
     après
    0.71
     clipped
    0.71
    方の
    0.71
    POSITIVE LOGITS
    t
    0.96
    ,
    0.77
     I
    0.74
    Ingredient
    0.69
    Old
    0.68
    Ade
    0.66
    Scale
    0.64
    Res
    0.64
     Concept
    0.64
    Push
    0.64
    Activations Density 0.003%

    No Known Activations