© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192455
    Prev
    Next
    INDEX
    Explanations

    mannerisms, isms, Manor

    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_4_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
    י
    1.51
    ي
    1.30
    i
    1.07
    ி
    0.99
    ،
    0.95
    ി
    0.90
     that
    0.88
     o
    0.83
    ك
    0.82
    ，
    0.81
    POSITIVE LOGITS
    us
    0.89
    al
    0.85
    esters
    0.81
    sembles
    0.80
    elina
    0.77
    ens
    0.77
    estimators
    0.73
    fixing
    0.72
    lene
    0.71
    em
    0.71
    Activations Density 0.008%

    No Known Activations