© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107190
    Prev
    Next
    INDEX
    Explanations

    past tense of "go"

    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
    Z
    1.20
     I
    1.13
     that
    1.11
    ли
    1.08
    I
    1.03
    R
    0.99
    ل
    0.96
    ן
    0.95
    M
    0.93
    Q
    0.93
    POSITIVE LOGITS
    са
    1.07
     are
    1.02
     as
    1.00
    ст
    0.95
     garçon
    0.95
    site
    0.93
    १
    0.89
     prennent
    0.87
    slave
    0.86
    subject
    0.85
    Activations Density 0.002%

    No Known Activations