© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198237
    Prev
    Next
    INDEX
    Explanations

    Jerusalem status as capital

    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_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ней
    0.58
     soutenir
    0.58
    يمان
    0.54
     imani
    0.51
    ଐ
    0.51
     приносит
    0.51
     godziny
    0.51
    尼
    0.50
     படை
    0.50
     tanque
    0.50
    POSITIVE LOGITS
    ipari
    0.50
    Hell
    0.44
    aç
    0.44
     Saj
    0.43
     Djibouti
    0.43
    acán
    0.42
     Yourself
    0.42
    woods
    0.41
    াগত
    0.41
    humidité
    0.41
    Activations Density 0.000%

    No Known Activations