© 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. 33481
    Prev
    Next
    INDEX
    Explanations

    dive deep into

    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
    ।
    1.03
    i
    0.95
    ي
    0.94
    e
    0.81
    ে
    0.76
     adaptations
    0.75
    y
    0.74
     isom
    0.73
    s
    0.72
    d
    0.71
    POSITIVE LOGITS
    ить
    0.67
    ēc
    0.61
    ě
    0.60
    ίας
    0.57
    已经被
    0.56
    ED
    0.54
    čil
    0.54
    葯
    0.54
    ils
    0.54
    ള
    0.54
    Activations Density 0.003%

    No Known Activations