© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107106
    Prev
    Next
    INDEX
    Explanations

    umami or umber or unmount

    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
    of
    1.57
    1.50
     is
    1.48
    '
    1.48
     of
    1.46
    ก
    1.45
    ।
    1.42
    ing
    1.41
    s
    1.41
    m
    1.40
    POSITIVE LOGITS
    νων
    1.06
     großen
    1.00
     اين
    0.99
    стта
    0.99
    ၆
    0.94
    دي
    0.93
    па
    0.93
    ని
    0.93
    둴
    0.93
     sinnv
    0.91
    Activations Density 0.000%

    No Known Activations