© 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. 85943
    Prev
    Next
    INDEX
    Explanations

    Yorgos, York, West, Grey

    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
    {
    0.76
     U
    0.73
    ע
    0.63
     I
    0.61
    Ꮖ
    0.60
    に向け
    0.59
    Ĩ
    0.58
    缨
    0.58
    栩
    0.57
    𝐇
    0.57
    POSITIVE LOGITS
    al
    0.83
    ap
    0.77
    am
    0.73
    ak
    0.68
    os
    0.67
    o
    0.66
    et
    0.63
    ax
    0.63
    ും
    0.63
    ेज
    0.63
    Activations Density 0.000%

    No Known Activations