© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34280
    Prev
    Next
    INDEX
    Explanations

    ai.google.dev

    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_31_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
    スタ
    0.40
    ковы
    0.39
    regression
    0.38
    esperienza
    0.38
     stack
    0.38
    тою
    0.38
    🧴
    0.37
     জন্ত
    0.37
    ruktur
    0.36
    ໃຊ້
    0.35
    POSITIVE LOGITS
    褚
    0.40
     توسط
    0.39
     تبلی
    0.39
    rible
    0.38
    MaxSize
    0.37
     최대한
    0.36
    PMC
    0.36
    ทำการ
    0.35
     CIO
    0.35
     Cheung
    0.34
    Activations Density 0.021%

    No Known Activations