© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57283
    Prev
    Next
    INDEX
    Explanations

    8.5 x 11 inches

    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_11_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
    屉
    0.45
    这
    0.44
    pectives
    0.43
    主义
    0.41
    螨
    0.41
    لان
    0.40
    回头
    0.40
    ك
    0.40
     ناخد
    0.40
    ítés
    0.39
    POSITIVE LOGITS
     as
    0.50
    assessment
    0.49
     zawier
    0.47
     hagas
    0.47
     igra
    0.46
     interferes
    0.46
     diminishes
    0.46
    Ｂ
    0.46
     एनिमल्स
    0.45
     impeding
    0.45
    Activations Density 0.011%

    No Known Activations