© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34027
    Prev
    Next
    INDEX
    Explanations

    Enterprise Architect

    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_3_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
     chế
    0.68
     sın
    0.64
     ramb
    0.63
    敂
    0.63
     đốc
    0.62
    های
    0.61
     astring
    0.61
     sloping
    0.60
     réglementation
    0.60
    в
    0.59
    POSITIVE LOGITS
    RA
    0.83
    IN
    0.82
    ي
    0.79
    oh
    0.78
    BA
    0.78
    ”。
    0.77
    RY
    0.76
    EL
    0.76
    ir
    0.75
     to
    0.75
    Activations Density 0.001%

    No Known Activations