© 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. 47022
    Prev
    Next
    INDEX
    Explanations

    album covers or albumen

    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
    (
    0.68
     від
    0.63
    čia
    0.61
    AssemblyName
    0.60
     Kräfte
    0.58
    {
    0.56
    u
    0.55
    ci
    0.54
    ga
    0.53
    ENO
    0.52
    POSITIVE LOGITS
    ने
    0.67
    örper
    0.65
     on
    0.65
    itt
    0.64
     albumin
    0.64
     neutrino
    0.64
     convoc
    0.64
    تين
    0.63
     internation
    0.62
    ”
    0.61
    Activations Density 0.000%

    No Known Activations