© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88122
    Prev
    Next
    INDEX
    Explanations

    compute initialization

    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
     ಇದನ್ನು
    0.60
     определяется
    0.58
    <unused95>
    0.57
     ܠ
    0.57
     fécond
    0.57
     система
    0.55
    求め
    0.55
    ﺧ
    0.55
    ﺻ
    0.55
    Ꮂ
    0.55
    POSITIVE LOGITS
    es
    0.99
    f
    0.85
    ve
    0.82
    ol
    0.82
    en
    0.81
    v
    0.81
    -
    0.81
    z
    0.80
    m
    0.78
    ir
    0.77
    Activations Density 0.002%

    No Known Activations