© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79267
    Prev
    Next
    INDEX
    Explanations

    vendor name extraction

    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
    ו
    2.06
    و
    1.96
    ุ
    1.50
    ری
    1.34
    ן
    1.33
    다
    1.32
    ně
    1.31
    ことで
    1.29
    น
    1.29
    the
    1.27
    POSITIVE LOGITS
    '
    1.88
    ’
    1.58
    Y
    1.48
    í
    1.35
    and
    1.29
    IMI
    1.14
    EN
    1.13
    inat
    1.13
    us
    1.12
    IM
    1.11
    Activations Density 0.000%

    No Known Activations