© 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. 91852
    Prev
    Next
    INDEX
    Explanations

    CPT coding

    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
    ಂಗ
    0.84
     carinatis
    0.82
    ’
    0.80
    м
    0.80
    enfance
    0.75
    ’।
    0.72
    ریان
    0.72
    ری
    0.71
    LAN
    0.71
    ам
    0.71
    POSITIVE LOGITS
    ne
    1.00
    1
    0.95
    ب
    0.89
    ll
    0.84
    st
    0.84
    w
    0.83
    ה
    0.82
    3
    0.81
    a
    0.80
    ა
    0.80
    Activations Density 0.008%

    No Known Activations