© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124651
    Prev
    Next
    INDEX
    Explanations

    dear friend, dear customer

    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
    (
    0.83
    i
    0.77
    <
    0.76
    >
    0.74
    5
    0.70
    ()
    0.64
    ’
    0.63
    o
    0.63
    1
    0.59
    9
    0.58
    POSITIVE LOGITS
    ה
    0.64
    ação
    0.62
    е
    0.62
    ные
    0.61
    äller
    0.59
     schweren
    0.59
    дования
    0.58
    ение
    0.58
    các
    0.58
     遅く
    0.57
    Activations Density 0.000%

    No Known Activations