© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151338
    Prev
    Next
    INDEX
    Explanations

    ys

    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
    m
    1.15
    म
    0.71
    in
    0.66
    م
    0.52
    ม
    0.51
    mə
    0.50
    meleri
    0.47
     matters
    0.46
    mment
    0.46
     mattered
    0.45
    POSITIVE LOGITS
    p
    0.82
    y
    0.81
    yed
    0.60
    pj
    0.52
    f
    0.52
    yh
    0.50
    pO
    0.50
    cary
    0.46
    pz
    0.46
    c
    0.46
    Activations Density 0.000%

    No Known Activations