© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135290
    Prev
    Next
    INDEX
    Explanations

    installments

    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_6_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
    ים
    1.26
    ות
    1.12
    स
    1.09
    ה
    1.09
    ל
    1.06
    A
    1.05
    ON
    1.03
    י
    0.99
    IN
    0.97
    S
    0.96
    POSITIVE LOGITS
    ación
    0.89
     ме
    0.88
    icação
    0.87
     прове
    0.86
     важно
    0.85
    azione
    0.84
     часу
    0.84
     determinación
    0.84
     нескольких
    0.83
     доб
    0.82
    Activations Density 0.000%

    No Known Activations