© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36283
    Prev
    Next
    INDEX
    Explanations

    quadratic formula

    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
    er
    0.96
    s
    0.86
    t
    0.82
    z
    0.81
    in
    0.76
    e
    0.75
    eritud
    0.73
    ed
    0.70
    el
    0.62
    ার
    0.62
    POSITIVE LOGITS
    It
    0.88
    ח
    0.74
    Sure
    0.73
    <unused532>
    0.71
    Love
    0.70
     활용
    0.70
    Zu
    0.70
    는
    0.68
    Em
    0.68
    Longueur
    0.68
    Activations Density 0.006%

    No Known Activations