© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157863
    Prev
    Next
    INDEX
    Explanations

    elected officials

    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
    is
    1.59
    は
    1.45
    కు
    1.40
    an
    1.30
    ان
    1.28
    은
    1.27
    কে
    1.25
    是
    1.19
    l
    1.17
    ки
    1.15
    POSITIVE LOGITS
     it
    0.96
     at
    0.95
     i
    0.95
    鸪
    0.87
     of
    0.85
    erna
    0.83
    fice
    0.82
     высокая
    0.82
    ums
    0.79
     პ
    0.77
    Activations Density 0.000%

    No Known Activations