© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152989
    Prev
    Next
    INDEX
    Explanations

    Xylos

    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_60_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
    is
    1.08
    in
    0.81
    म
    0.59
    se
    0.56
    IS
    0.53
    م
    0.47
    ਸ
    0.47
    Η
    0.46
    t
    0.45
    m
    0.44
    POSITIVE LOGITS
    pa
    0.66
    cy
    0.66
    thy
    0.63
    da
    0.62
    pat
    0.62
    ni
    0.61
    thi
    0.61
    nata
    0.60
    pre
    0.59
    pu
    0.59
    Activations Density 0.001%

    No Known Activations