© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45280
    Prev
    Next
    INDEX
    Explanations

    for this reason

    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_10_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
    is
    1.31
    to
    0.88
    al
    0.79
    ())
    0.77
    ey
    0.77
    ти
    0.75
    ب
    0.75
    de
    0.74
    at
    0.73
    к
    0.70
    POSITIVE LOGITS
     (
    0.86
     gave
    0.84
     but
    0.82
     đưa
    0.78
    ה
    0.76
     d
    0.75
     dell
    0.75
     veteran
    0.74
     delle
    0.72
     năm
    0.71
    Activations Density 0.000%

    No Known Activations