© 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. 41157
    Prev
    Next
    INDEX
    Explanations

    colossal dimensions (feet tall)

    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
    Negative Logits
    әк
    0.44
     pâ
    0.43
     '@/
    0.43
     discorso
    0.42
     absorption
    0.42
     Fü
    0.42
     অসংখ্য
    0.42
     predicates
    0.41
    髮
    0.41
    類
    0.41
    POSITIVE LOGITS
     itd
    0.41
     опубликован
    0.41
    adan
    0.40
    ocumented
    0.39
    ajan
    0.38
    itans
    0.38
     paint
    0.38
     effective
    0.37
    uant
    0.37
    fighters
    0.37
    Activations Density 0.002%

    No Known Activations