© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90455
    Prev
    Next
    INDEX
    Explanations

    Nahuatl, Mandarin, Hindi, Urdu, Hawaiian, Chinese

    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_3_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
    ل
    0.72
    n
    0.68
    اد
    0.68
    拉克
    0.68
    A
    0.66
    지
    0.66
    ى
    0.64
    دد
    0.64
     Վ
    0.63
    لنا
    0.63
    POSITIVE LOGITS
     are
    0.84
    on
    0.82
    ing
    0.77
    ों
    0.75
    of
    0.70
    ओं
    0.68
    and
    0.67
    u
    0.66
    ی
    0.64
    ING
    0.64
    Activations Density 0.000%

    No Known Activations