© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45562
    Prev
    Next
    INDEX
    Explanations

    flattening the curve

    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_13_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
    瑞士
    0.37
    Swiss
    0.36
    wirtschaft
    0.36
    랍
    0.36
    Portrait
    0.35
    ritt
    0.35
    Director
    0.35
    ill
    0.35
    raq
    0.35
    rö
    0.34
    POSITIVE LOGITS
     pide
    0.39
     Yeti
    0.39
    ქმ
    0.38
     Tumblr
    0.37
     crept
    0.37
    ઠી
    0.37
     나오고
    0.37
    ]')
    0.37
    。
    0.36
     Saito
    0.36
    Activations Density 0.007%

    No Known Activations