© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37992
    Prev
    Next
    INDEX
    Explanations

    list bullet

    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_57_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
     nos
    0.41
     entonces
    0.41
     मेन
    0.39
     contrary
    0.39
    รม
    0.38
    ങ്ങനെ
    0.38
     ई
    0.37
     Efforts
    0.37
     minority
    0.36
     Instruction
    0.36
    POSITIVE LOGITS
     Pode
    0.47
     pode
    0.43
    pont
    0.41
    站
    0.41
     entwick
    0.39
     શહેર
    0.38
     FON
    0.38
    ников
    0.37
     walker
    0.37
    물을
    0.37
    Activations Density 0.001%

    No Known Activations