© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35373
    Prev
    Next
    INDEX
    Explanations

    flutes

    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_7_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
    ки
    1.59
    ik
    1.51
    on
    1.45
    il
    1.44
    ت
    1.41
    im
    1.37
    ف
    1.32
    as
    1.27
    т
    1.23
    ak
    1.20
    POSITIVE LOGITS
     러
    0.82
    EDS
    0.75
     là
    0.74
     の
    0.72
     protracted
    0.71
     steaming
    0.71
    じて
    0.71
     vaguely
    0.71
    اتی
    0.70
    AN
    0.70
    Activations Density 0.000%

    No Known Activations