© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110316
    Prev
    Next
    INDEX
    Explanations

    ends with "some"

    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
    c
    1.22
    '
    1.20
    เป็น
    1.13
    ang
    1.06
    .
    1.01
    но
    0.99
    1
    0.99
    ied
    0.99
    ny
    0.96
    is
    0.95
    POSITIVE LOGITS
    지
    0.98
    in
    0.96
    h
    0.94
     montañas
    0.93
     десятки
    0.92
    。</
    0.91
    ร
    0.90
     lágrimas
    0.89
    iş
    0.89
     zahlreiche
    0.88
    Activations Density 0.000%

    No Known Activations