© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78193
    Prev
    Next
    INDEX
    Explanations

    Cameroon

    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_0_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
    к
    1.69
    ва
    1.66
    та
    1.54
    ке
    1.52
    -
    1.45
    ’
    1.43
     provincia
    1.41
    יל
    1.38
    ית
    1.35
    માં
    1.34
    POSITIVE LOGITS
    s
    2.05
    h
    1.73
    i
    1.66
    in
    1.59
    to
    1.52
    pre
    1.52
    z
    1.50
     and
    1.47
    post
    1.40
    pe
    1.39
    Activations Density 0.000%

    No Known Activations