© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235704
    Prev
    Next
    INDEX
    Explanations

    information about

    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_25_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
    nV
    0.42
    кир
    0.40
    ：「
    0.39
    水道
    0.39
    ＊＊
    0.38
    ிலும்
    0.38
     кана
    0.38
     チ
    0.38
    ખો
    0.38
    ズノ
    0.38
    POSITIVE LOGITS
     dispar
    0.45
    häuse
    0.45
     look
    0.44
     loopholes
    0.43
     negativ
    0.43
     survival
    0.43
     jurispr
    0.42
     그렇게
    0.41
     restrictions
    0.41
     hypothetical
    0.41
    Activations Density 0.000%

    No Known Activations