© 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. 33267
    Prev
    Next
    INDEX
    Explanations

    thorny

    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
    ط
    0.85
    ل
    0.76
    ח
    0.75
    ৫
    0.71
    ৮
    0.71
    ม
    0.68
    ล
    0.68
    ด
    0.68
    מ
    0.66
     {
    0.66
    POSITIVE LOGITS
    der
    0.80
    developed
    0.75
    cylinder
    0.73
    s
    0.71
    soluble
    0.70
    species
    0.69
    soldiers
    0.67
    shank
    0.66
    sung
    0.66
    ductory
    0.66
    Activations Density 0.000%

    No Known Activations