© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83741
    Prev
    Next
    INDEX
    Explanations

    userID, mouseY, Salmon

    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_0_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
    ה
    1.63
    ۰
    1.60
    ם
    1.35
    д
    1.26
    t
    1.15
    v
    1.15
    ют
    1.14
    ้
    1.13
     свет
    1.13
    으며
    1.12
    POSITIVE LOGITS
     in
    2.09
    1.91
    ut
    1.71
     for
    1.56
    og
    1.46
     at
    1.45
     be
    1.39
     (
    1.30
    ik
    1.29
     are
    1.27
    Activations Density 0.000%

    No Known Activations