© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2376
    Prev
    Next
    INDEX
    Explanations

    php code blocks

    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_39_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
    菄
    0.41
    ipped
    0.40
    拗
    0.39
     камер
    0.38
     সম্বন্ধে
    0.38
    $-[
    0.37
     архіви
    0.37
     checkFor
    0.36
     যুগ
    0.36
     cdot
    0.36
    POSITIVE LOGITS
     evaluations
    0.41
    jos
    0.40
    ês
    0.39
     campaigns
    0.38
    uniq
    0.38
    ঃ
    0.38
    Start
    0.37
    loc
    0.36
     परी
    0.36
     xay
    0.36
    Activations Density 0.002%

    No Known Activations