© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226901
    Prev
    Next
    INDEX
    Explanations

    prodigy

    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
    Negative Logits
    3
    0.90
    8
    0.88
    6
    0.88
    >
    0.83
    :
    0.82
    5
    0.79
    이나
    0.75
    7
    0.74
    ↵
    0.73
    ()
    0.73
    POSITIVE LOGITS
    t
    0.92
    d
    0.82
    р
    0.74
    dew
    0.72
    féle
    0.71
    l
    0.71
    ਰ
    0.71
    metre
    0.70
    ુ
    0.69
    きれい
    0.68
    Activations Density 0.000%

    No Known Activations