© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15458
    Prev
    Next
    INDEX
    Explanations

    Schultz

    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_15_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
    ಯ್
    0.50
     carn
    0.50
    packaged
    0.48
     హి
    0.48
     tiss
    0.48
     worldwide
    0.48
    蛳
    0.47
    ᆼ
    0.47
     glob
    0.46
     милли
    0.46
    POSITIVE LOGITS
     मर्यादा
    0.50
    <td>
    0.48
    ote
    0.47
    uku
    0.46
    狷
    0.46
    oran
    0.46
    ore
    0.44
     více
    0.44
    ран
    0.44
    ouveau
    0.44
    Activations Density 0.000%

    No Known Activations