© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85260
    Prev
    Next
    INDEX
    Explanations

    true/false literals

    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_23_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
     trú
    0.38
     मिलेगी
    0.38
    गौर
    0.38
    ાલુ
    0.38
    ్వర
    0.37
    КТ
    0.37
    刧
    0.36
    監
    0.36
    weichen
    0.36
    RICT
    0.36
    POSITIVE LOGITS
     Kimber
    0.42
     exodus
    0.42
     Pi
    0.39
    oush
    0.38
     necess
    0.38
     relative
    0.38
     households
    0.38
    iments
    0.37
    üh
    0.37
    ization
    0.37
    Activations Density 0.003%

    No Known Activations