© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 4-GEMMASCOPE-2-TRANSCODER-262K
    4. 195633
    Prev
    Next
    INDEX
    Explanations

    Gulag System

    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_4_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
     be
    0.19
    in
    0.18
    ↵↵
    0.17
    ering
    0.15
    K
    0.15
     a
    0.14
     to
    0.14
    H
    0.14
     in
    0.13
    ats
    0.13
    POSITIVE LOGITS
    剞
    0.16
    いくつかの
    0.15
    SRPI
    0.15
     fortiter
    0.14
     outstretched
    0.14
    ت
    0.14
    א
    0.14
    ע
    0.14
     patitth
    0.13
     yattha
    0.13
    Activations Density 0.001%

    No Known Activations