© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201834
    Prev
    Next
    INDEX
    Explanations

    Nijika Ijiri

    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_6_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
    \
    0.74
     \
    0.52
    ark
    0.50
    ist
    0.50
     in
    0.49
    -
    0.48
    </h1>
    0.48
    </h2>
    0.46
    </b>
    0.46
    </sub>
    0.45
    POSITIVE LOGITS
     audioEngine
    0.50
    LuaPush
    0.47
    PlayerSelector
    0.45
     pueda
    0.45
     beschik
    0.45
     Sereth
    0.45
     attham
    0.43
     Mikolai
    0.43
     pudo
    0.42
     piatta
    0.42
    Activations Density 0.000%

    No Known Activations