© 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. 78422
    Prev
    Next
    INDEX
    Explanations

    clubhouse

    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
    سين
    1.64
    ائي
    1.57
    (
    1.55
    د
    1.52
    스의
    1.51
    سك
    1.45
    سي
    1.44
    سون
    1.43
    리
    1.41
    يا
    1.34
    POSITIVE LOGITS
    ri
    1.85
    rt
    1.78
    that
    1.76
    ne
    1.73
    red
    1.70
    ry
    1.67
    w
    1.59
    li
    1.55
    low
    1.49
    la
    1.48
    Activations Density 0.000%

    No Known Activations