© 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. 88852
    Prev
    Next
    INDEX
    Explanations

    Olympic Park

    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
    an
    1.13
    a
    0.87
    r
    0.84
    one
    0.74
    ر
    0.70
    ب
    0.70
    aný
    0.69
    在
    0.67
     in
    0.66
    ки
    0.66
    POSITIVE LOGITS
    ES
    0.74
    یں
    0.72
    ěné
    0.69
    -
    0.68
    نی
    0.67
    س
    0.64
    ‌است
    0.64
    ESI
    0.64
    ě
    0.63
    EN
    0.61
    Activations Density 0.000%

    No Known Activations