© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91592
    Prev
    Next
    INDEX
    Explanations

    Advanced Micro Devices

    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_3_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
    و
    0.74
    ো
    0.73
    يي
    0.71
    ا
    0.71
    дини
    0.70
    г
    0.68
    ו
    0.67
    ш
    0.66
    ش
    0.65
    it
    0.65
    POSITIVE LOGITS
    us
    0.64
    Վ
    0.54
    ۔
    0.53
    І
    0.52
    ly
    0.51
    Il
    0.51
    ICK
    0.51
    ling
    0.50
    UT
    0.49
    ania
    0.49
    Activations Density 0.003%

    No Known Activations