© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78469
    Prev
    Next
    INDEX
    Explanations

    Vas followed by other tokens

    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_0_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
    1.63
    ৬
    1.55
    on
    1.52
    is
    1.51
     in
    1.22
    ot
    1.20
    ır
    1.20
    ní
    1.19
    ə
    1.19
    ри
    1.18
    POSITIVE LOGITS
    s
    1.71
    ↵↵
    1.50
     to
    1.39
    0
    1.25
    ీ
    1.25
    ओं
    1.20
    ีย
    1.19
    ס
    1.16
    ティ
    1.14
     badminton
    1.14
    Activations Density 0.000%

    No Known Activations