© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158253
    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_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
    世界的
    0.43
    $.\
    0.38
    设定
    0.37
     העולם
    0.36
    เข้าไป
    0.35
    શ્વ
    0.35
    <unused12>
    0.35
    SequentialGroup
    0.35
     envie
    0.34
    传
    0.34
    POSITIVE LOGITS
     Wo
    0.60
    Wo
    0.60
     wer
    0.54
    Wer
    0.51
    Wh
    0.50
     wo
    0.49
     WER
    0.49
     Во
    0.48
     Wer
    0.47
     Wur
    0.46
    Activations Density 0.000%

    No Known Activations