© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37200
    Prev
    Next
    INDEX
    Explanations

    sort

    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_50_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
    щенко
    0.41
    雁
    0.41
    igans
    0.40
    udging
    0.40
    Fight
    0.39
    issan
    0.39
    श्रे
    0.39
     Fight
    0.38
    וג
    0.37
    ajul
    0.36
    POSITIVE LOGITS
    рова
    0.44
    𝗿
    0.44
     Napoli
    0.39
    rbuf
    0.39
    rivation
    0.38
    रव
    0.37
     nop
    0.37
     colonia
    0.37
    naie
    0.37
    ronomie
    0.36
    Activations Density 0.000%

    No Known Activations