© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126587
    Prev
    Next
    INDEX
    Explanations

    raw application options

    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_3_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
    ut
    0.77
    w
    0.72
    il
    0.66
    _
    0.62
    ain
    0.61
    ling
    0.60
    ೇ
    0.59
    ui
    0.59
    ິ
    0.59
    ri
    0.58
    POSITIVE LOGITS
    e
    0.95
    at
    0.80
    ו
    0.78
    يها
    0.76
    ك
    0.75
    a
    0.71
    كا
    0.69
    ا
    0.68
    f
    0.67
    יא
    0.65
    Activations Density 0.000%

    No Known Activations