© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87502
    Prev
    Next
    INDEX
    Explanations

    Philip Glass, Knight, Jackson, Johnson

    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_3_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
    ați
    0.65
    ватися
    0.59
    ра
    0.58
    】：
    0.58
    ENCIAS
    0.58
    рати
    0.57
    दानी
    0.55
    の
    0.55
    lytres
    0.54
    WAB
    0.54
    POSITIVE LOGITS
     for
    0.70
    ৫
    0.58
     priming
    0.55
    สอง
    0.55
     arv
    0.55
     $
    0.54
     दो
    0.54
     o
    0.52
     ack
    0.52
     philanthropic
    0.51
    Activations Density 0.000%

    No Known Activations