© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83317
    Prev
    Next
    INDEX
    Explanations

    say articles

    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_53_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
    aciju
    0.42
     Tala
    0.39
     आपला
    0.38
    oretic
    0.38
    ㄋ
    0.37
     Valk
    0.37
     brunt
    0.37
     आपली
    0.36
     очередной
    0.36
    ştik
    0.35
    POSITIVE LOGITS
    ദ്
    0.42
     thei
    0.37
     thes
    0.37
    맞
    0.37
    ưng
    0.35
    MINOR
    0.34
    thel
    0.33
    serializers
    0.33
     حوالے
    0.32
    toHaveBeenCalled
    0.32
    Activations Density 0.008%

    No Known Activations