© 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. 30284
    Prev
    Next
    INDEX
    Explanations

    CNN

    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
    í
    0.82
    lager
    0.80
     Букмекердик
    0.74
    ای
    0.72
    usak
    0.72
     Букмекерлер
    0.71
    larni
    0.69
    lardan
    0.68
    á
    0.68
    蝟
    0.68
    POSITIVE LOGITS
     ב
    0.75
     be
    0.73
     a
    0.72
    ?
    0.71
     ו
    0.70
     и
    0.70
     purposefully
    0.66
     et
    0.65
     будет
    0.64
     maliciously
    0.64
    Activations Density 0.007%

    No Known Activations