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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6940
    Prev
    Next
    INDEX
    Explanations

    date and time

    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_39_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
    ्युनिकेशन
    0.31
     BONDS
    0.31
    ஷ்
    0.29
    ichia
    0.28
     অধিদপ্তর
    0.27
    uri
    0.27
    sterling
    0.27
    꽁
    0.26
    
    0.26
     Pg
    0.26
    POSITIVE LOGITS
     тек
    0.31
     입력
    0.31
     neur
    0.30
     фильм
    0.30
     olmuş
    0.30
    writeInt
    0.30
     nucl
    0.29
    浊
    0.29
     gió
    0.29
     accord
    0.28
    Activations Density 0.001%

    No Known Activations