© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235590
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     செய்க
    0.46
     comes
    0.43
     goog
    0.42
     coeff
    0.40
     Southern
    0.40
    ++);
    0.40
     V
    0.38
     போய்
    0.38
    ளே
    0.37
    鏉
    0.37
    POSITIVE LOGITS
    Muito
    0.40
    enciado
    0.38
    อ่อน
    0.38
    unci
    0.38
     محاض
    0.37
     Miao
    0.37
    मेर
    0.36
    极
    0.36
    中心的
    0.36
    लेषण
    0.35
    Activations Density 0.002%

    No Known Activations