© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129861
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    i
    1.57
    p
    1.54
    f
    1.52
    l
    1.50
    an
    1.49
    v
    1.45
    h
    1.32
    ان
    1.29
    c
    1.29
    ak
    1.28
    POSITIVE LOGITS
    ка
    1.23
    ы
    1.04
    2
    1.02
    습니다
    1.00
    :
    0.93
    می
    0.93
    νά
    0.91
    تی
    0.89
    ның
    0.89
    𝗻
    0.89
    Activations Density 0.000%

    No Known Activations