© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14903
    Prev
    Next
    INDEX
    Explanations

    ability and impossibility

    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_13_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
     [
    0.40
     bew
    0.40
    ка
    0.38
    tive
    0.38
     bacter
    0.38
     rése
    0.37
     intre
    0.37
    прово
    0.37
     icin
    0.36
    ان
    0.36
    POSITIVE LOGITS
     McG
    0.40
    McG
    0.39
     emphas
    0.39
     eponym
    0.38
    ClearedBy
    0.38
    鎬
    0.37
     sported
    0.37
    Tổng
    0.36
     ساتھ
    0.36
    AbsolutePath
    0.35
    Activations Density 0.071%

    No Known Activations