© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44487
    Prev
    Next
    INDEX
    Explanations

    Stone, Plastic, Gate, fish

    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
    ح
    0.76
     Fuels
    0.70
    have
    0.65
    ا
    0.64
     Tablets
    0.64
    o
    0.64
     (
    0.62
    It
    0.60
    letter
    0.59
    िन
    0.59
    POSITIVE LOGITS
     nourrir
    0.71
     deactivated
    0.67
     mercredi
    0.66
     avait
    0.64
     noyau
    0.62
    p
    0.60
     viewport
    0.60
     feit
    0.60
     abide
    0.59
     croire
    0.59
    Activations Density 0.001%

    No Known Activations