© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60660
    Prev
    Next
    INDEX
    Explanations

    auxiliary verb "does"

    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_2_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
     in
    1.48
    the
    1.48
    在
    1.45
    و
    1.44
    In
    1.38
    一
    1.38
    to
    1.34
    ?
    1.34
    أ
    1.33
    ุ
    1.27
    POSITIVE LOGITS
    ла
    1.54
    -
    1.45
    ли
    1.42
     раствор
    1.34
    ки
    1.30
     can
    1.25
    lerinin
    1.25
    ларга
    1.25
    lerinde
    1.23
    ih
    1.20
    Activations Density 0.009%

    No Known Activations