© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198792
    Prev
    Next
    INDEX
    Explanations

    Penhaligon

    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_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    at
    0.63
    il
    0.61
    O
    0.59
     épaisse
    0.57
    т
    0.57
    geoType
    0.55
    searchDisplay
    0.55
    icidal
    0.53
     killings
    0.51
    saturation
    0.51
    POSITIVE LOGITS
    מ
    0.64
    נ
    0.56
    बु
    0.56
     aventura
    0.54
    א
    0.54
    م
    0.53
    ام
    0.52
    الم
    0.52
    साल
    0.52
    ཇ
    0.51
    Activations Density 0.000%

    No Known Activations