© 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. 15558
    Prev
    Next
    INDEX
    Explanations

    transformers import

    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
    ቧ
    0.40
    咭
    0.39
     m
    0.38
     eco
    0.37
     nostalgia
    0.36
    ashire
    0.36
     темати
    0.36
    ễ
    0.36
     persuasive
    0.36
     blacklist
    0.36
    POSITIVE LOGITS
    BinaryOperation
    0.37
     teamTable
    0.37
    SizeType
    0.35
     пропор
    0.35
    𝜌
    0.35
    จ่าย
    0.33
    ⚤
    0.33
    дям
    0.33
    的全
    0.33
     Tyrone
    0.33
    Activations Density 0.000%

    No Known Activations