© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221547
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    的游戏
    0.54
    面临
    0.52
    宝
    0.49
    居然
    0.49
    依然
    0.48
    遗
    0.47
    陇
    0.47
    তারপর
    0.47
     তারপর
    0.46
    威
    0.46
    POSITIVE LOGITS
    q
    0.61
    h
    0.57
    ic
    0.56
    un
    0.56
    res
    0.55
    ide
    0.55
    ari
    0.55
    im
    0.54
    ad
    0.54
    ch
    0.54
    Activations Density 0.000%

    No Known Activations