© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63988
    Prev
    Next
    INDEX
    Explanations

    Wi

    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_59_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
    כון
    0.43
    pruch
    0.41
    सूस
    0.40
    otonic
    0.39
     '-')
    0.39
    kuensi
    0.39
    胿
    0.38
    atian
    0.38
    atot
    0.38
    setItem
    0.38
    POSITIVE LOGITS
    :
    0.40
     Και
    0.39
     them
    0.38
    ――
    0.38
     increasing
    0.38
     sparked
    0.38
     rising
    0.37
    ;
    0.37
    ๆ
    0.37
    יו
    0.36
    Activations Density 0.000%

    No Known Activations