© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40804
    Prev
    Next
    INDEX
    Explanations

    bestbettergoodvery

    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_11_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
     customization
    0.32
    Н
    0.32
     الاص
    0.31
    الن
    0.31
    кай
    0.30
    ૂત
    0.30
    Time
    0.30
    ка
    0.29
    الص
    0.29
     مو
    0.28
    POSITIVE LOGITS
    รก
    0.37
    d
    0.37
     Bottles
    0.37
    मुळे
    0.36
    lem
    0.35
    z
    0.35
    b
    0.34
    हरु
    0.33
    łę
    0.33
    mere
    0.33
    Activations Density 0.160%

    No Known Activations