© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204333
    Prev
    Next
    INDEX
    Explanations

    SQL query column names

    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_25_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
     مولانا
    0.47
    ‘
    0.41
     २०२
    0.39
    ITC
    0.38
    으
    0.38
    '",
    0.36
    ated
    0.36
    क़
    0.35
     ١
    0.35
    알
    0.33
    POSITIVE LOGITS
     campsite
    0.39
    ড়ের
    0.39
     camping
    0.39
     waktu
    0.38
     drying
    0.38
     কেমন
    0.38
     Jadi
    0.38
     akibat
    0.38
     kering
    0.38
     dryness
    0.38
    Activations Density 0.003%

    No Known Activations