© 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. 168142
    Prev
    Next
    INDEX
    Explanations

    you liked/discussed/learned

    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
     created
    0.49
    acic
    0.47
     stwor
    0.43
     did
    0.40
    宣
    0.40
    uose
    0.38
     launched
    0.38
     notor
    0.37
     रही
    0.36
     lightning
    0.35
    POSITIVE LOGITS
    ကလေး
    0.43
     dipende
    0.42
     зависит
    0.41
    取决于
    0.41
    এম
    0.39
    滗
    0.38
     คู่
    0.38
     अवलंब
    0.38
    entwicklung
    0.38
    propertyName
    0.37
    Activations Density 0.002%

    No Known Activations