© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24627
    Prev
    Next
    INDEX
    Explanations

    home

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    잔
    0.39
    灏
    0.35
    Allocator
    0.35
    妿
    0.35
    ipher
    0.34
    امن
    0.33
     zipcode
    0.32
     Precip
    0.32
    iero
    0.32
    KeyboardView
    0.32
    POSITIVE LOGITS
     homes
    3.41
     Homes
    3.23
    homes
    3.23
    Homes
    3.23
     home
    1.95
    home
    1.82
    ホーム
    1.76
     홈
    1.64
     HOM
    1.63
    홈
    1.61
    Activations Density 0.043%

    No Known Activations