© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105733
    Prev
    Next
    INDEX
    Explanations

    trope

    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_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
    ۰
    1.21
    ти
    1.15
    st
    1.04
    تين
    1.01
    precio
    1.00
    те
    0.98
    ០
    0.98
    0.96
    ৭
    0.89
    tern
    0.89
    POSITIVE LOGITS
     as
    1.22
    ル
    1.04
     that
    1.00
     be
    0.98
     to
    0.96
    的
    0.96
    ਰ
    0.96
    の
    0.95
    וס
    0.91
    ो
    0.91
    Activations Density 0.002%

    No Known Activations