© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107551
    Prev
    Next
    INDEX
    Explanations

    hebrew and yiddish words

    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
     are
    1.13
     on
    1.11
    ING
    1.06
    는
    1.02
    ко
    1.01
    의
    1.01
    е
    1.00
     is
    0.95
    го
    0.94
    ın
    0.93
    POSITIVE LOGITS
    i
    1.13
    ról
    1.13
    that
    1.04
    し
    1.02
    PanelVisual
    0.95
     benefícios
    0.95
    꾿
    0.93
    ur
    0.92
    ra
    0.89
    wają
    0.89
    Activations Density 0.004%

    No Known Activations