© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133592
    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_6_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
    at
    1.13
    ing
    0.95
     for
    0.93
    for
    0.91
    -
    0.87
    ive
    0.81
    /
    0.81
    ie
    0.79
    ed
    0.77
    from
    0.76
    POSITIVE LOGITS
    ند
    0.64
    ния
    0.58
    ק
    0.58
    اب
    0.57
    нан
    0.57
    вання
    0.57
    鏉
    0.57
     моду
    0.54
    к
    0.54
    ﻛ
    0.54
    Activations Density 0.000%

    No Known Activations