© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 213065
    Prev
    Next
    INDEX
    Explanations

    matsuri

    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
    i
    0.99
     It
    0.96
    npcs
    0.95
    )،
    0.92
    ेशन
    0.91
    )。
    0.91
    க்கழக
    0.88
     JsonConvert
    0.87
     Tiến
    0.87
    ri
    0.85
    POSITIVE LOGITS
    я
    1.22
    ą
    1.21
    í
    1.18
    н
    1.13
    á
    1.13
    à
    1.13
    ü
    1.11
    ING
    1.09
    ia
    1.08
    é
    1.01
    Activations Density 0.000%

    No Known Activations