© 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. 107409
    Prev
    Next
    INDEX
    Explanations

    flaws

    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
    ۰
    1.54
    0
    1.35
    ع
    1.22
    ۵
    1.19
    ری
    1.18
    רי
    1.16
    2
    1.16
    baiki
    1.13
    for
    1.12
    5
    1.12
    POSITIVE LOGITS
    لي
    0.87
     gehe
    0.87
    š
    0.86
    ž
    0.86
     provoz
    0.85
     a
    0.84
    il
    0.84
    ين
    0.84
    }.
    0.84
    其他
    0.84
    Activations Density 0.000%

    No Known Activations