© 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. 130800
    Prev
    Next
    INDEX
    Explanations

    articles and determiners

    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
    ceğine
    0.43
     መጠቀም
    0.38
     शुक्ला
    0.38
     አገልግሎ
    0.34
    tség
    0.34
    ៗ
    0.33
    ถมศึกษา
    0.33
     victimes
    0.32
     যাহা
    0.32
     calibr
    0.31
    POSITIVE LOGITS
     a
    0.42
     eine
    0.42
     einer
    0.41
     an
    0.41
     sebuah
    0.40
    ട്ട
    0.39
     einen
    0.39
     একটি
    0.38
     μια
    0.37
     een
    0.37
    Activations Density 0.021%

    No Known Activations