© 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. 131207
    Prev
    Next
    INDEX
    Explanations

    inherits or descriptors

    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_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
    リ
    1.04
     to
    0.97
     by
    0.95
    ０
    0.93
     kaum
    0.87
    ۰
    0.86
    )"
    0.85
     titers
    0.85
     tags
    0.84
     статьи
    0.83
    POSITIVE LOGITS
    f
    1.39
    t
    1.30
    h
    1.29
    k
    1.23
    e
    1.07
    kker
    0.98
    a
    0.98
    g
    0.98
    ة
    0.95
    い
    0.90
    Activations Density 0.000%

    No Known Activations