© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38517
    Prev
    Next
    INDEX
    Explanations

    eat

    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_57_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
    iapan
    0.48
    yld
    0.47
    hawk
    0.45
    יות
    0.42
    eck
    0.42
    ি
    0.42
    aque
    0.41
    tus
    0.41
    ينا
    0.40
    eed
    0.39
    POSITIVE LOGITS
    enca
    0.41
    '@
    0.38
    inten
    0.37
    ai
    0.36
     إن
    0.34
    ansi
    0.34
    urten
    0.34
    /@
    0.34
     कुशल
    0.34
    atai
    0.34
    Activations Density 0.000%

    No Known Activations