© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113226
    Prev
    Next
    INDEX
    Explanations

    Zionism

    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_2_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
    n
    1.34
    on
    1.29
    t
    1.17
    y
    1.16
     in
    1.11
    in
    1.10
    en
    1.09
    ’
    1.07
    ca
    1.02
    ا
    1.00
    POSITIVE LOGITS
    د
    1.36
    ای
    1.27
    áme
    1.09
    ä
    1.09
    AY
    1.07
    ет
    1.06
    い
    1.06
    یت
    1.05
     for
    1.03
    า
    1.03
    Activations Density 0.000%

    No Known Activations