© 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. 161939
    Prev
    Next
    INDEX
    Explanations

    years of experience

    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
    ,
    1.52
    มัน
    1.23
     as
    1.20
    מ
    1.17
    ก็
    1.16
    ล
    1.02
    ม
    0.99
    로
    0.98
    ร
    0.98
    ני
    0.95
    POSITIVE LOGITS
    3
    1.41
    5
    1.16
    4
    1.15
    ية
    1.09
    ٣
    1.00
    ний
    0.95
    pricht
    0.95
    pinimg
    0.95
    for
    0.94
    fe
    0.94
    Activations Density 0.000%

    No Known Activations