© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209934
    Prev
    Next
    INDEX
    Explanations

    spins or turns

    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_10_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
    の
    0.37
    に
    0.36
    는
    0.34
    в
    0.34
    ен
    0.33
    म
    0.33
    ב
    0.33
    ف
    0.31
    は
    0.31
    의
    0.31
    POSITIVE LOGITS
     inflict
    0.32
     ৪
    0.31
     weren
    0.31
     Ι
    0.30
     bescherm
    0.30
     afficher
    0.30
    ជីវ
    0.30
    ប្រើ
    0.30
     néhány
    0.30
     இரண்டு
    0.29
    Activations Density 0.003%

    No Known Activations