© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145818
    Prev
    Next
    INDEX
    Explanations

    leisure activities

    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
    )
    1.65
    のない
    1.35
    ;
    1.27
    ﺔ
    1.27
    )».
    1.26
    の違い
    1.25
    ).
    1.23
    nH
    1.21
    ﻪ
    1.21
     scolded
    1.20
    POSITIVE LOGITS
    in
    2.48
    i
    2.45
    an
    2.02
    ب
    1.92
     for
    1.82
    ي
    1.79
    ت
    1.73
    ק
    1.73
    e
    1.66
    ש
    1.65
    Activations Density 0.000%

    No Known Activations