© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196421
    Prev
    Next
    INDEX
    Explanations

    real product image

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Equations
    0.39
     표준
    0.37
    ଣ
    0.37
    óz
    0.35
     upperBound
    0.35
     প্রত্যাখ্যান
    0.35
    Tmp
    0.34
    ಗಳಿಗೆ
    0.34
    铵
    0.33
    гий
    0.33
    POSITIVE LOGITS
     Wirkung
    0.43
    ermat
    0.41
     खोला
    0.41
     effects
    0.39
    ինչ
    0.38
     Spal
    0.38
     brinda
    0.38
     halls
    0.38
     Doris
    0.38
     Nisha
    0.37
    Activations Density 0.000%

    No Known Activations