© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216059
    Prev
    Next
    INDEX
    Explanations

    choose, select, case

    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_31_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
    可以选择
    0.40
    choose
    0.38
     choose
    0.37
    雬
    0.37
    Choose
    0.36
     customised
    0.35
     createCanvas
    0.35
     кв
    0.35
     выбирать
    0.35
    ឪ
    0.34
    POSITIVE LOGITS
    กีฬา
    0.39
    emate
    0.38
     میچ
    0.36
    tod
    0.35
    梱包
    0.35
     Riv
    0.34
     emblematic
    0.34
     athlet
    0.34
     competit
    0.34
     Sync
    0.34
    Activations Density 0.000%

    No Known Activations