© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196485
    Prev
    Next
    INDEX
    Explanations

    modellanguage codes

    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_27_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
    مط
    0.36
     locul
    0.34
    Parker
    0.34
    den
    0.33
    ielle
    0.32
    #
    0.32
    elift
    0.32
    Kl
    0.31
     distributes
    0.31
     partitioned
    0.31
    POSITIVE LOGITS
     पैर
    0.40
     фев
    0.33
     febbraio
    0.32
    仅
    0.32
    امد
    0.31
     இருப்பது
    0.31
     স্বাভাবিক
    0.30
    不已
    0.30
    プロジェクト
    0.30
    有名
    0.30
    Activations Density 0.000%

    No Known Activations