© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213494
    Prev
    Next
    INDEX
    Explanations

    wuxia, xianxia, pruritus

    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_5_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
    2.08
     can
    1.63
    ли
    1.30
    ла
    1.20
    '
    1.13
    RO
    1.02
    են
    1.01
    잍
    0.95
    יות
    0.92
    isso
    0.91
    POSITIVE LOGITS
    s
    1.52
    in
    1.42
     in
    1.20
    0
    1.16
    ς
    1.14
    ی
    1.13
    ों
    1.10
    ۰
    1.05
    3
    1.04
    I
    1.03
    Activations Density 0.000%

    No Known Activations