© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 214949
    Prev
    Next
    INDEX
    Explanations

    API Guide Documentation

    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_31_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
    詄
    0.45
    lder
    0.36
    浱
    0.33
     العلوم
    0.33
    arly
    0.32
     Soma
    0.32
    __);
    0.32
    वन
    0.32
     transcendence
    0.32
    лку
    0.31
    POSITIVE LOGITS
    概述
    0.41
    Overview
    0.41
     Overview
    0.40
    overview
    0.39
    概要
    0.38
     روش
    0.38
     প্রবাহ
    0.37
    描述
    0.36
     fer
    0.35
     نح
    0.35
    Activations Density 0.001%

    No Known Activations