© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45140
    Prev
    Next
    INDEX
    Explanations

    cereal, licorice, alimony

    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_10_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
    ou
    1.13
    ו
    1.09
    on
    1.04
    ي
    1.04
    ak
    1.00
     notre
    0.99
    i
    0.95
    es
    0.92
    ad
    0.90
    و
    0.89
    POSITIVE LOGITS
    }\
    0.89
    flav
    0.89
    }=(
    0.87
     Много
    0.85
    ган
    0.84
    蚓
    0.82
     reorgan
    0.80
    都
    0.80
    txt
    0.79
    }=\
    0.79
    Activations Density 0.020%

    No Known Activations