© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82739
    Prev
    Next
    INDEX
    Explanations

    anonymous lecturer

    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_29_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
     Grove
    0.47
    Grove
    0.40
    POINT
    0.37
    व
    0.36
    oter
    0.36
    re
    0.36
    ô
    0.36
     ionizing
    0.35
    具备
    0.34
     Mercado
    0.33
    POSITIVE LOGITS
     ahuv
    0.44
     dépass
    0.42
    嘍
    0.39
     "["
    0.39
     "\(
    0.38
     puisque
    0.38
     labios
    0.38
    Bren
    0.37
     gà
    0.37
     involunt
    0.36
    Activations Density 0.001%

    No Known Activations