© 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. 126624
    Prev
    Next
    INDEX
    Explanations

    ultraviolet radiation and colitis

    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
    ра
    0.89
    at
    0.84
     heeft
    0.83
    า
    0.81
    0.78
    يد
    0.76
    off
    0.73
    NIE
    0.71
     deze
    0.70
    ND
    0.68
    POSITIVE LOGITS
    :
    0.77
    =
    0.75
    bs
    0.73
    gger
    0.72
    ؎
    0.71
    ح
    0.70
    ၷ
    0.70
    <
    0.68
    gll
    0.67
    gia
    0.66
    Activations Density 0.000%

    No Known Activations