© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196412
    Prev
    Next
    INDEX
    Explanations

    oil and fat

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    当时
    0.46
    rlig
    0.40
    咶
    0.40
     currant
    0.39
    бран
    0.38
    aric
    0.38
     ward
    0.38
    attho
    0.37
    rijk
    0.37
    當時
    0.37
    POSITIVE LOGITS
    mot
    0.46
    COT
    0.44
    more
    0.44
    m
    0.43
    cot
    0.43
    coat
    0.40
    cote
    0.40
     Schild
    0.39
    тной
    0.39
    MORE
    0.38
    Activations Density 0.000%

    No Known Activations