© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35334
    Prev
    Next
    INDEX
    Explanations

    prizes, raffles, giveaways, winning

    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_7_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
     σε
    0.75
     in
    0.72
    ंक्शन
    0.69
    在
    0.69
    رى
    0.65
    ли
    0.64
    ية
    0.63
    חיל
    0.63
     quiescent
    0.63
     parochial
    0.61
    POSITIVE LOGITS
    ikt
    0.95
    y
    0.92
     ')
    0.87
    alu
    0.87
    atu
    0.84
    ct
    0.83
    ett
    0.82
     (
    0.82
     н
    0.82
    \
    0.80
    Activations Density 0.008%

    No Known Activations