© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131020
    Prev
    Next
    INDEX
    Explanations

    authorization headers

    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_25_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
     প্রেক্ষিতে
    0.38
     Mandatory
    0.34
     Respondent
    0.33
    覤
    0.33
     Mailing
    0.33
     ಸಂದ
    0.33
     Algonquin
    0.33
    گز
    0.32
    AIRE
    0.32
    賖
    0.32
    POSITIVE LOGITS
    flood
    0.39
     accident
    0.36
     nouvel
    0.36
    accident
    0.35
     słu
    0.35
    uç
    0.35
    act
    0.34
    vacc
    0.34
    base
    0.33
    then
    0.33
    Activations Density 0.002%

    No Known Activations