© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46214
    Prev
    Next
    INDEX
    Explanations

    list items after digits/letters like B or ii

    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_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    طة
    0.19
     decisão
    0.17
     Zweck
    0.17
     हल्का
    0.17
    棫
    0.16
     molécule
    0.16
    鎵
    0.16
    appareil
    0.16
     Besucher
    0.16
    gré
    0.15
    POSITIVE LOGITS
    Dij
    0.18
     jumps
    0.18
     films
    0.16
     weekdays
    0.16
     multiplies
    0.16
    猕
    0.16
     articles
    0.15
     digests
    0.15
     tems
    0.15
     assets
    0.15
    Activations Density 0.001%

    No Known Activations