© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11432
    Prev
    Next
    INDEX
    Explanations

    trend changes and reversals

    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_40_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
    pesas
    0.41
    수로
    0.37
    スラ
    0.37
    ḿ
    0.37
    Mum
    0.36
     sequence
    0.36
    ļ
    0.36
    ຸ
    0.36
    មុ
    0.35
    ाब
    0.35
    POSITIVE LOGITS
     bursts
    0.46
     pauses
    0.41
    trace
    0.39
     pause
    0.39
     çö
    0.38
     piercings
    0.38
    дис
    0.38
     piled
    0.37
    ব্রি
    0.37
     dwells
    0.37
    Activations Density 0.086%

    No Known Activations