© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41344
    Prev
    Next
    INDEX
    Explanations

    advocate for

    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_11_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
    ၅
    0.48
     Bahnhof
    0.48
    屽
    0.48
    ﻛ
    0.46
    ค์
    0.45
     saloon
    0.44
     लोन
    0.44
     Bumble
    0.43
    σης
    0.43
    ธ์
    0.43
    POSITIVE LOGITS
    p
    0.66
    in
    0.65
    id
    0.59
    lista
    0.57
    adim
    0.55
    ad
    0.54
    list
    0.54
    cert
    0.54
    are
    0.54
    y
    0.52
    Activations Density 0.000%

    No Known Activations