© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193614
    Prev
    Next
    INDEX
    Explanations

    masters of Camouflage, Ships, Puppets, diving

    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_15_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
    hline
    0.28
     position
    0.28
     figure
    0.27
     le
    0.27
     line
    0.26
     been
    0.26
     ü
    0.26
    erde
    0.26
     prince
    0.26
     operate
    0.25
    POSITIVE LOGITS
     یہودی
    0.30
     صہیونیوں
    0.28
    Sushi
    0.27
    性价比
    0.27
    Correo
    0.26
     یہودیوں
    0.26
    য্
    0.26
    激光
    0.26
     مذہب
    0.25
    న
    0.25
    Activations Density 0.003%

    No Known Activations