© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47211
    Prev
    Next
    INDEX
    Explanations

    a growing number of

    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
    Negative Logits
    ي
    0.81
    i
    0.79
    ב
    0.74
    b
    0.73
    בל
    0.72
    ↵↵
    0.72
    ”
    0.71
    )
    0.71
    t
    0.70
    d
    0.68
    POSITIVE LOGITS
    1
    0.69
    leyici
    0.66
    udor
    0.62
    ்துற
    0.59
    ॉजिस्ट
    0.59
    veyor
    0.57
    agog
    0.57
    cluded
    0.57
    
    0.56
    ानि
    0.55
    Activations Density 0.000%

    No Known Activations