© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170514
    Prev
    Next
    INDEX
    Explanations

    addition followed by parenthesis

    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_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    范围
    0.29
    远
    0.28
    位
    0.28
     最高
    0.28
     ख़ास
    0.27
    Bit
    0.27
     rar
    0.26
     koff
    0.26
    Ary
    0.26
     świata
    0.26
    POSITIVE LOGITS
    鰍
    0.29
     Playhouse
    0.28
    nemidophorus
    0.28
    erdings
    0.28
     equivalently
    0.27
     가서
    0.27
    aeskeygenassist
    0.27
    書の
    0.26
     రాయ
    0.26
    crose
    0.26
    Activations Density 0.002%

    No Known Activations