© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31869
    Prev
    Next
    INDEX
    Explanations

    table

    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
    padă
    0.83
    आई
    0.79
     också
    0.73
    ﮐ
    0.72
     kudos
    0.70
    ()=>{
    0.69
    ள்ளனர்
    0.69
    =>{
    0.68
    خدام
    0.68
    تباينه
    0.67
    POSITIVE LOGITS
    an
    1.19
    ри
    1.08
    א
    1.04
    for
    1.00
    ان
    0.98
    ש
    0.96
    ב
    0.92
    ম
    0.91
    ח
    0.91
    that
    0.90
    Activations Density 0.012%

    No Known Activations