© 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. 86428
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific explanations

    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
    m
    0.91
     It
    0.91
    in
    0.68
    g
    0.64
     In
    0.62
    scrap
    0.57
    K
    0.57
    now
    0.56
    墘
    0.55
    ed
    0.55
    POSITIVE LOGITS
     preservatives
    0.80
     particulates
    0.69
     analogs
    0.69
     anions
    0.67
     muons
    0.66
    ༸
    0.66
     خارجی
    0.64
     financiers
    0.64
     detergents
    0.63
     corticosteroids
    0.63
    Activations Density 0.000%

    No Known Activations