© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200947
    Prev
    Next
    INDEX
    Explanations

    affordable

    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_50_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
     shēng
    0.47
    标识
    0.41
    νή
    0.40
     abrigo
    0.39
    infrastructure
    0.38
     distinguish
    0.37
     reorganize
    0.36
    輩
    0.36
     المسؤول
    0.36
    يرين
    0.36
    POSITIVE LOGITS
    脲
    0.39
    $&$
    0.37
     یورو
    0.37
    厓
    0.37
    toJson
    0.37
    ^{+}$.
    0.36
    USION
    0.35
    语法
    0.35
    문에
    0.35
     Rhythm
    0.35
    Activations Density 0.000%

    No Known Activations