© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36556
    Prev
    Next
    INDEX
    Explanations

    Ellen DeGeneres, Eleanor, Ellie

    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_3_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
     on
    0.96
    ক
    0.95
    a
    0.84
    ه
    0.83
    ق
    0.82
    к
    0.81
    ي
    0.80
    ۔
    0.78
    ت
    0.76
    נ
    0.73
    POSITIVE LOGITS
    ور
    0.75
    om
    0.73
    ні
    0.70
    фек
    0.69
    τια
    0.68
    पूर
    0.68
    रा
    0.67
    phants
    0.67
    डीए
    0.66
    aksha
    0.66
    Activations Density 0.000%

    No Known Activations