© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13918
    Prev
    Next
    INDEX
    Explanations

    legal claims and standards

    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_15_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
     utilisant
    0.14
    чина
    0.13
    ستخدم
    0.13
    当我
    0.13
    Ч
    0.13
    ใน
    0.13
     nutrient
    0.13
     conditioners
    0.13
    ใช
    0.13
     nutrients
    0.13
    POSITIVE LOGITS
    f
    0.16
    da
    0.15
    ari
    0.15
     advogado
    0.14
    aru
    0.14
    d
    0.14
    電機
    0.14
    UTCDate
    0.14
    ','"+
    0.14
    URA
    0.14
    Activations Density 0.015%

    No Known Activations