© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50811
    Prev
    Next
    INDEX
    Explanations

    entity/attribute

    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_30_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
     outputs
    0.40
    䟧
    0.39
     eigenfunctions
    0.38
    طلاب
    0.37
    এবং
    0.37
    霢
    0.37
    ‌شده
    0.37
     пределах
    0.37
    ადა
    0.36
     dateTime
    0.36
    POSITIVE LOGITS
    lovakia
    0.39
    ulho
    0.39
     []);
    0.39
     Sure
    0.38
     вре
    0.37
    ühle
    0.36
    PERCENT
    0.36
    ơm
    0.35
    ache
    0.35
     wala
    0.35
    Activations Density 0.001%

    No Known Activations