© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200537
    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_12_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
     about
    0.54
    اب
    0.51
    श
    0.51
    ש
    0.51
    Sh
    0.50
     wygl
    0.50
     ow
    0.50
    食
    0.48
    $
    0.48
    コン
    0.46
    POSITIVE LOGITS
    ní
    0.60
     человек
    0.59
    墓志
    0.58
     جري
    0.57
     ලැබ
    0.57
     Ministère
    0.57
    ৯
    0.55
    namespaces
    0.55
    ٩
    0.55
     Globes
    0.54
    Activations Density 0.000%

    No Known Activations