© 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. 40615
    Prev
    Next
    INDEX
    Explanations

    size parameter

    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
    ני
    0.74
     ")
    0.61
     splitpos
    0.61
     Mysore
    0.58
    anio
    0.57
     Mena
    0.57
    ल
    0.57
     respectivos
    0.57
    Overflow
    0.56
    ว์
    0.56
    POSITIVE LOGITS
    с
    0.84
    economic
    0.73
    ea
    0.73
    e
    0.73
    đ
    0.69
    el
    0.67
    ier
    0.64
    น
    0.60
    ూ
    0.59
    ができる
    0.59
    Activations Density 0.020%

    No Known Activations