© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27115
    Prev
    Next
    INDEX
    Explanations

    jot down

    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_10_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
    usion
    0.54
     I
    0.52
    ,
    0.48
    t
    0.48
    น
    0.47
    ts
    0.46
     sebuah
    0.46
    ting
    0.46
    ;
    0.46
     vang
    0.44
    POSITIVE LOGITS
    ે
    0.57
    ަލ
    0.50
    ü
    0.48
    ﻓ
    0.46
     încep
    0.45
    ບໍ
    0.44
    м
    0.44
     corazón
    0.44
    arım
    0.43
    ུ
    0.43
    Activations Density 0.025%

    No Known Activations