© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 219020
    Prev
    Next
    INDEX
    Explanations

    IX surveillance interfaces

    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_16_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
    <html>
    0.51
     `'\\
    0.51
    ров
    0.45
     `:`,
    0.45
     meticul
    0.45
     offres
    0.45
     scopes
    0.45
    ্যক
    0.45
    PAS
    0.44
     <<"
    0.44
    POSITIVE LOGITS
     chieftain
    0.48
    idencia
    0.46
     ಸೇವ
    0.46
     pedra
    0.46
     crusade
    0.46
    सेवा
    0.45
     Denk
    0.45
     blame
    0.44
     hospitable
    0.44
     یون
    0.43
    Activations Density 0.000%

    No Known Activations