© 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. 4637
    Prev
    Next
    INDEX
    Explanations

    Pdf Reader

    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
    朔
    0.40
     Popov
    0.39
    ার্থী
    0.37
    apollo
    0.37
    .$\
    0.37
     పని
    0.36
    มาณ
    0.36
    kele
    0.36
    㕵
    0.36
    wai
    0.36
    POSITIVE LOGITS
    ató
    0.39
    зона
    0.38
    Hands
    0.37
     나오는
    0.37
    Zona
    0.37
    Zone
    0.37
    愣
    0.36
    óm
    0.35
    ่อม
    0.35
     आतंक
    0.35
    Activations Density 0.004%

    No Known Activations