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

    Neuronpedia

    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. 144428
    Prev
    Next
    INDEX
    Explanations

    businessman

    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
    in
    1.76
    ৫
    1.52
     averted
    1.44
    ı
    1.41
    ী
    1.38
    ৭
    1.31
    ir
    1.30
     I
    1.27
    সহ
    1.23
    jų
    1.20
    POSITIVE LOGITS
    ס
    1.84
    تها
    1.80
     was
    1.31
    ങ്ങൾ
    1.31
    A
    1.29
    ాల
    1.28
    تد
    1.25
    斯
    1.23
    ну
    1.22
    고
    1.20
    Activations Density 0.000%

    No Known Activations