© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7649
    Prev
    Next
    INDEX
    Explanations

    Now we

    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_39_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
    ✙
    0.39
    Roger
    0.38
    ണിത്
    0.37
    叐
    0.37
     Roger
    0.37
     віднов
    0.37
     inversion
    0.37
    низ
    0.36
     рабо
    0.36
     мало
    0.35
    POSITIVE LOGITS
     volunteered
    0.35
    Gil
    0.35
     লিমি
    0.35
    (**
    0.35
    Figure
    0.35
    purch
    0.34
    Spotify
    0.34
     knew
    0.34
    Bea
    0.34
     acknowledges
    0.34
    Activations Density 0.017%

    No Known Activations