© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109158
    Prev
    Next
    INDEX
    Explanations

    malayalam script elements

    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_1_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
     (
    1.58
    و
    1.25
     -
    1.14
    r
    1.10
    a
    1.06
     of
    1.05
     been
    1.05
    1
    1.03
    ו
    1.02
    ات
    1.01
    POSITIVE LOGITS
    ِي
    0.94
    しくは
    0.89
    ние
    0.86
     StringSet
    0.82
    ش
    0.80
     Sommers
    0.80
    粈
    0.79
    َ
    0.75
    ́u
    0.75
    ě
    0.75
    Activations Density 0.000%

    No Known Activations