© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166348
    Prev
    Next
    INDEX
    Explanations

    getters and setters

    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_34_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
    Sym
    0.40
     Portug
    0.38
     ജെ
    0.37
     جانا
    0.36
     Sym
    0.36
     Dataset
    0.36
    Swiss
    0.35
    ('');
    0.35
     Вики
    0.35
    addir
    0.35
    POSITIVE LOGITS
    roben
    0.37
    inelli
    0.37
    imen
    0.35
    imantan
    0.35
     xuất
    0.35
     пропор
    0.34
     പ്രതീക്ഷ
    0.34
     இனி
    0.34
     फैलाने
    0.34
     MC
    0.34
    Activations Density 0.000%

    No Known Activations