© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90482
    Prev
    Next
    INDEX
    Explanations

    ISO-8859-1 or Latin-1 and sampling AQL 8

    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
    т
    0.92
    ור
    0.90
    ת
    0.80
    त
    0.79
    る
    0.78
    ল
    0.77
    ב
    0.74
    ל
    0.73
     o
    0.72
    。...
    0.71
    POSITIVE LOGITS
    f
    0.97
    ↵↵
    0.83
    w
    0.74
    я
    0.70
    otonic
    0.67
    fice
    0.66
    uracy
    0.64
    wys
    0.64
    i
    0.64
    v
    0.64
    Activations Density 0.001%

    No Known Activations