© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101756
    Prev
    Next
    INDEX
    Explanations

    Flask, CORS, socket, bcrypt

    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_14_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
     Chica
    0.57
     玄
    0.55
     Sánchez
    0.54
     遊ん
    0.54
    玴
    0.52
    日英
    0.52
     Jimenez
    0.51
     चक्रवृद्धि
    0.51
    oustic
    0.50
     WORLD
    0.49
    POSITIVE LOGITS
    s
    0.53
     Procedure
    0.49
    dois
    0.48
    ा
    0.48
    Il
    0.48
     V
    0.48
    V
    0.48
    sapp
    0.47
    Bu
    0.47
    Procedure
    0.47
    Activations Density 0.000%

    No Known Activations