© 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. 129543
    Prev
    Next
    INDEX
    Explanations

    มาก

    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
    า
    1.09
    b
    1.03
    s
    1.02
    m
    1.00
    ا
    1.00
    ة
    0.98
    ul
    0.94
    ின்
    0.86
    त
    0.86
    ing
    0.85
    POSITIVE LOGITS
    لي
    1.07
    ان
    1.04
     некоторые
    1.00
     arabe
    1.00
    ０
    0.97
     ejemplo
    0.92
     време
    0.92
     источник
    0.91
     дочери
    0.91
     maliciously
    0.91
    Activations Density 0.000%

    No Known Activations