© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227905
    Prev
    Next
    INDEX
    Explanations

    delay in

    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
     (
    1.29
    ۔
    0.98
    ן
    0.93
    the
    0.89
    that
    0.87
    os
    0.86
     [
    0.85
    จะ
    0.85
    א
    0.83
    SE
    0.83
    POSITIVE LOGITS
     efectuar
    1.11
     beho
    1.10
     pontos
    1.05
    vať
    1.03
     bañ
    1.01
    ᅴ
    1.00
    場合
    0.99
     plástico
    0.98
     طبي
    0.98
    した後
    0.98
    Activations Density 0.000%

    No Known Activations