© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196049
    Prev
    Next
    INDEX
    Explanations

    has trouble

    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_27_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
    樂
    0.33
     Kimmel
    0.31
    <unused1863>
    0.31
     sạch
    0.31
    を結
    0.31
    श्रे
    0.30
     Kathleen
    0.30
    巿
    0.30
     Peu
    0.30
    🌏
    0.29
    POSITIVE LOGITS
    ng
    0.32
     conf
    0.31
     organs
    0.31
     motorcycle
    0.30
     class
    0.30
     protocols
    0.29
    idency
    0.29
     shotgun
    0.29
     motorcycles
    0.29
     warmth
    0.29
    Activations Density 0.000%

    No Known Activations