© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82623
    Prev
    Next
    INDEX
    Explanations

    Wander or wanderer

    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_0_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
    in
    2.80
    า
    2.38
    ia
    2.09
    o
    1.78
    ן
    1.73
    ic
    1.63
    io
    1.54
    ร
    1.49
    c
    1.48
    inę
    1.42
    POSITIVE LOGITS
    كان
    1.75
     judíos
    1.46
     compradores
    1.45
     мастеров
    1.39
    ंना
    1.38
     officielles
    1.38
     empresarios
    1.38
     étudiants
    1.37
     académicos
    1.36
     специалистов
    1.32
    Activations Density 0.000%

    No Known Activations