© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162596
    Prev
    Next
    INDEX
    Explanations

    code ending or setup

    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_31_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
    ímetros
    0.30
    ዎች
    0.29
    backgroundColor
    0.29
    brug
    0.29
    皂
    0.28
    Glass
    0.27
    彌
    0.27
    ዣ
    0.27
    cityName
    0.27
     Wirtschaft
    0.26
    POSITIVE LOGITS
     goin
    0.33
     frequ
    0.33
    CLUDING
    0.33
    querysearch
    0.33
     fréqu
    0.32
    unning
    0.31
     ভাবী
    0.30
    éget
    0.29
     destinée
    0.29
    ERNAL
    0.28
    Activations Density 0.001%

    No Known Activations