© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87379
    Prev
    Next
    INDEX
    Explanations

    GO

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    alysis
    0.49
     Horses
    0.44
    collectibles
    0.39
    ा
    0.39
     ಮ
    0.38
    scaping
    0.38
    roversial
    0.38
    destructive
    0.37
     Hammer
    0.37
    corona
    0.37
    POSITIVE LOGITS
    i
    0.49
    ي
    0.49
    urez
    0.47
    یم
    0.45
    o
    0.41
     fellow
    0.41
     this
    0.40
    uky
    0.38
    욤
    0.38
    ᴙ
    0.38
    Activations Density 0.000%

    No Known Activations