© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199678
    Prev
    Next
    INDEX
    Explanations

    biscuits

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ński
    0.51
    倒
    0.42
    㧡
    0.41
    entious
    0.40
    нії
    0.40
    ისტ
    0.39
    鎮
    0.39
    নিতে
    0.38
    اند
    0.38
    નિ
    0.38
    POSITIVE LOGITS
     Garr
    0.39
     Rican
    0.39
     Ricardo
    0.38
    랠
    0.38
     socks
    0.37
    O
    0.37
    Larry
    0.37
    cuda
    0.37
    edo
    0.37
     Socks
    0.37
    Activations Density 0.000%

    No Known Activations