© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261280
    Prev
    Next
    INDEX
    Explanations

    your are

    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_5_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
    ت
    1.39
    ש
    1.31
    는
    1.17
    ۔
    1.17
    は
    1.13
    О
    1.02
    އ
    1.02
    ת
    0.99
    С
    0.99
    в
    0.97
    POSITIVE LOGITS
    า
    0.76
    il
    0.74
    ip
    0.72
    ada
    0.67
     sería
    0.67
    ak
    0.66
     是
    0.66
    ↵↵
    0.64
    ia
    0.63
     IPython
    0.63
    Activations Density 0.000%

    No Known Activations