© 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. 56546
    Prev
    Next
    INDEX
    Explanations

    or

    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
    الن
    0.48
    f
    0.45
    아
    0.43
    အ
    0.42
     alan
    0.40
     up
    0.40
    Т
    0.40
    नल
    0.39
    О
    0.39
    いて
    0.38
    POSITIVE LOGITS
     ឬ
    0.48
    ení
    0.46
     océano
    0.40
     或者
    0.40
    ષ્
    0.39
     maqu
    0.39
     ειδ
    0.38
     ຫຼື
    0.38
     లేదా
    0.38
    يز
    0.37
    Activations Density 0.002%

    No Known Activations