© 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. 113223
    Prev
    Next
    INDEX
    Explanations

    daring, darling

    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
     to
    1.48
    d
    1.23
    st
    1.15
    ↵
    1.13
    el
    1.13
     of
    1.03
     is
    1.02
    mith
    1.02
    le
    1.00
    p
    0.98
    POSITIVE LOGITS
    ي
    1.17
    у
    1.13
    де
    1.09
    сро
    1.08
    )،
    1.06
    ура
    1.01
     není
    1.00
    و
    1.00
    ر
    1.00
     It
    0.99
    Activations Density 0.009%

    No Known Activations