© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87434
    Prev
    Next
    INDEX
    Explanations

    say "R" words

    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_60_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
     Name
    0.48
    book
    0.47
     Un
    0.46
     Res
    0.45
    place
    0.45
    fold
    0.45
     Read
    0.45
     Опреде
    0.44
    tour
    0.43
    y
    0.43
    POSITIVE LOGITS
     sub
    0.52
     struts
    0.48
    σταση
    0.42
    }^{*}=
    0.41
    стям
    0.41
     MT
    0.40
    Ṕ
    0.40
    <0xA2>
    0.39
    スイ
    0.39
     subwoofer
    0.39
    Activations Density 0.001%

    No Known Activations