© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113477
    Prev
    Next
    INDEX
    Explanations

    elevenlabs

    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_2_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
     have
    1.08
    0
    0.96
     and
    0.95
     with
    0.94
    на
    0.85
    ﻩ
    0.84
    siniz
    0.80
     Dutchman
    0.80
     پیغمبر
    0.79
     windfall
    0.79
    POSITIVE LOGITS
    in
    1.68
    es
    1.59
    ar
    1.54
    h
    1.54
    un
    1.52
    y
    1.26
    an
    1.25
    i
    1.25
    ใน
    1.23
    a
    1.23
    Activations Density 0.002%

    No Known Activations