© 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. 231426
    Prev
    Next
    INDEX
    Explanations

    ACH, EFT, ACH/EFT

    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
    ↵↵
    1.41
    in
    1.11
     or
    1.02
    }
    0.98
    ek
    0.95
     née
    0.95
    th
    0.91
    an
    0.90
    is
    0.90
    ak
    0.89
    POSITIVE LOGITS
    т
    1.07
    وانات
    0.98
    اعه
    0.91
    твы
    0.88
    ക്കാര
    0.86
    وان
    0.85
    쳐
    0.83
    ارت
    0.77
    ನೆಯ
    0.77
    냈다
    0.77
    Activations Density 0.000%

    No Known Activations