© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28468
    Prev
    Next
    INDEX
    Explanations

    frequency (Hz)

    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_10_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
    માં
    0.83
    లో
    0.73
    ↵
    0.69
    er
    0.68
    ان
    0.68
    ന്ന
    0.64
     doesn
    0.63
     visit
    0.61
     can
    0.61
    يك
    0.61
    POSITIVE LOGITS
     Stomach
    0.80
    vej
    0.67
    keras
    0.66
    ita
    0.64
     Favorites
    0.62
     आइट
    0.62
     이야기
    0.61
    cef
    0.61
    ရင်း
    0.60
    ς
    0.59
    Activations Density 0.017%

    No Known Activations