© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15076
    Prev
    Next
    INDEX
    Explanations

    task scripting or medication

    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
    嘏
    0.38
    ιση
    0.34
    макра
    0.34
    ዋ
    0.32
     Lorsque
    0.32
     régler
    0.32
    ᱗
    0.32
    цыя
    0.31
    लेश्वर
    0.31
     versie
    0.31
    POSITIVE LOGITS
    ly
    0.47
     an
    0.43
    ign
    0.38
    org
    0.38
        
    0.36
     a
    0.36
    </code>
    0.35
     p
    0.35
    igh
    0.34
    real
    0.34
    Activations Density 0.000%

    No Known Activations