© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66307
    Prev
    Next
    INDEX
    Explanations

    modelm after whitespace

    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_41_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
    LIB
    0.42
    気の
    0.42
     ATI
    0.41
    NK
    0.39
     Iran
    0.39
    \*
    0.38
     LIB
    0.38
     attir
    0.38
    ATS
    0.37
     deposito
    0.37
    POSITIVE LOGITS
     combinado
    0.38
    បត្តិ
    0.38
     hashtag
    0.38
     makeSound
    0.37
     শিখ
    0.36
    sberg
    0.36
    ยัง
    0.35
    ="#"><
    0.35
     Kombination
    0.35
     Goog
    0.35
    Activations Density 0.014%

    No Known Activations