© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206916
    Prev
    Next
    INDEX
    Explanations

    .tar.gz archive files

    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_6_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
    in
    1.40
    ä
    1.38
    f
    1.23
    au
    1.22
    ans
    1.20
    v
    1.16
    1
    1.15
    し
    1.15
     it
    1.14
    to
    1.14
    POSITIVE LOGITS
     способности
    0.82
     торго
    0.79
    εν
    0.76
     coefficient
    0.75
    uties
    0.75
     конвер
    0.75
    ate
    0.75
    ьте
    0.75
    ت
    0.74
     deem
    0.74
    Activations Density 0.000%

    No Known Activations