© 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. 85991
    Prev
    Next
    INDEX
    Explanations

    active area

    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
     Exodus
    0.60
    िंग्स
    0.60
    անի
    0.59
    ’
    0.59
    annt
    0.59
    ر
    0.56
    ’).
    0.55
     agglut
    0.54
    erci
    0.53
    ل
    0.53
    POSITIVE LOGITS
    in
    0.80
    머니
    0.71
    c
    0.67
    ند
    0.61
    and
    0.60
    ன்
    0.59
    لی
    0.59
    지만
    0.58
    ことを
    0.58
    {~
    0.58
    Activations Density 0.004%

    No Known Activations