© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83809
    Prev
    Next
    INDEX
    Explanations

    html.parser

    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_23_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
    ની
    0.16
    æt
    0.16
    涳
    0.16
     некоторое
    0.15
     เศษ
    0.15
    感觉到
    0.15
    楽し
    0.15
     частини
    0.15
    疤
    0.15
    zeich
    0.15
    POSITIVE LOGITS
     orders
    0.19
     mutable
    0.18
     refractory
    0.18
     outgrowth
    0.18
     lustre
    0.17
     lift
    0.17
     alias
    0.17
     idempotent
    0.17
    ाइंड
    0.16
     alloy
    0.16
    Activations Density 0.002%

    No Known Activations