© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125378
    Prev
    Next
    INDEX
    Explanations

    regenerate, regenerative

    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_3_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
     It
    0.66
    ao
    0.64
     Of
    0.57
     NFL
    0.57
    igslist
    0.57
    の見
    0.57
    ’
    0.57
     Chicago
    0.56
     Who
    0.56
    。“
    0.56
    POSITIVE LOGITS
     regularity
    0.75
    क
    0.75
    ک
    0.75
     approximating
    0.73
    ز
    0.73
    ק
    0.73
    し
    0.71
    ক
    0.69
    یم
    0.68
    ся
    0.68
    Activations Density 0.000%

    No Known Activations