© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57347
    Prev
    Next
    INDEX
    Explanations

    electron beam, emission, bombardment

    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_11_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
     ک
    0.64
     C
    0.55
    C
    0.54
    c
    0.52
     Fe
    0.49
    м
    0.49
    ን
    0.48
     nouvel
    0.48
     H
    0.47
    ace
    0.47
    POSITIVE LOGITS
     teknologi
    0.66
    内容
    0.55
     Teknologi
    0.55
    orescent
    0.54
    <tr>
    0.53
     عندما
    0.53
    ⿳
    0.53
    🚐
    0.53
    优雅
    0.52
     পরিপ্রে
    0.52
    Activations Density 0.031%

    No Known Activations