© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45550
    Prev
    Next
    INDEX
    Explanations

    only slight, friends, constraint, medication

    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_10_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
    z
    0.83
    I
    0.82
    t
    0.80
    کار
    0.72
    LV
    0.72
    ä
    0.72
    os
    0.71
    exceptions
    0.69
    LE
    0.68
    y
    0.68
    POSITIVE LOGITS
     THE
    0.86
     galley
    0.75
     belieb
    0.70
     CHARACTER
    0.69
     przew
    0.69
     secundaria
    0.69
     vlas
    0.69
     WATER
    0.68
     PHOT
    0.68
     provoz
    0.68
    Activations Density 0.001%

    No Known Activations