© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9730
    Prev
    Next
    INDEX
    Explanations

    organic productions

    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_13_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
     be
    0.53
     plas
    0.52
     주
    0.51
     amines
    0.49
     polymers
    0.48
     بي
    0.47
     функ
    0.47
     ю
    0.47
     н
    0.47
     alken
    0.47
    POSITIVE LOGITS
     AppBar
    0.47
     prohibited
    0.46
     Texts
    0.46
    嵯
    0.46
    bogen
    0.45
     exclamation
    0.44
    یدہ
    0.43
    летнего
    0.43
    </u>
    0.43
    Ǻ
    0.43
    Activations Density 0.010%

    No Known Activations