© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235826
    Prev
    Next
    INDEX
    Explanations

    import csv, json, def

    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_32_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
     twórc
    0.43
    ơn
    0.41
     tìm
    0.41
     naturels
    0.39
     طبي
    0.39
    字母
    0.37
    ⠛
    0.37
     Hind
    0.35
    排除
    0.35
     লিখিত
    0.35
    POSITIVE LOGITS
    financial
    0.42
     financial
    0.41
     calcula
    0.39
     calcul
    0.38
    collage
    0.38
     फाइनेंशियल
    0.37
     +'
    0.37
    Nes
    0.36
     aprecia
    0.36
     calcular
    0.36
    Activations Density 0.000%

    No Known Activations