© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144153
    Prev
    Next
    INDEX
    Explanations

    Parsons, parsimonious

    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_0_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
    '
    1.63
    你
    1.61
     has
    1.51
    ↵↵
    1.47
    ’
    1.43
    3
    1.42
     tradu
    1.38
     as
    1.35
     este
    1.30
    ↵
    1.27
    POSITIVE LOGITS
    ர்
    1.34
    ul
    1.27
    ı
    1.25
     in
    1.24
    houses
    1.21
    ா
    1.18
    摖
    1.18
    ë
    1.14
    가가
    1.10
    holes
    1.09
    Activations Density 0.000%

    No Known Activations