© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8632
    Prev
    Next
    INDEX
    Explanations

    c++ programming language

    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_13_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
    ᱩ
    0.26
    क्ले
    0.25
    /</
    0.24
     bears
    0.24
     anal
    0.24
     conc
    0.24
     चिंता
    0.23
     ].
    0.23
     deletes
    0.23
     रहेगा
    0.23
    POSITIVE LOGITS
    ’
    0.34
    rington
    0.30
    isan
    0.28
    ased
    0.27
     sarebbero
    0.26
    abad
    0.26
    aji
    0.25
     erano
    0.25
    avano
    0.25
     Eulerian
    0.25
    Activations Density 0.131%

    No Known Activations