© 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. 27532
    Prev
    Next
    INDEX
    Explanations

    ibler

    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
     ancak
    0.67
    at
    0.66
     L
    0.61
     וע
    0.60
     alue
    0.59
     adalah
    0.56
     用户
    0.55
     on
    0.55
     dve
    0.55
     H
    0.55
    POSITIVE LOGITS
    F
    0.73
    T
    0.61
     Балтбет
    0.59
    depression
    0.59
    processor
    0.58
    परेशन
    0.57
    R
    0.57
    Worldwide
    0.57
     Иң
    0.56
    factory
    0.55
    Activations Density 0.000%

    No Known Activations