© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43194
    Prev
    Next
    INDEX
    Explanations

    reasoning behind

    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_13_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
    el
    0.60
    ↵
    0.54
    as
    0.52
    Лю
    0.52
    P
    0.52
    erp
    0.52
    Чу
    0.51
    oled
    0.51
    Неза
    0.51
    omone
    0.50
    POSITIVE LOGITS
    /
    0.57
    ів
    0.53
     and
    0.52
     wouldn
    0.50
     υψη
    0.50
    גר
    0.50
     değişiklik
    0.49
     includ
    0.48
     بشكل
    0.47
     Augustin
    0.47
    Activations Density 0.021%

    No Known Activations