© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 239939
    Prev
    Next
    INDEX
    Explanations

    quick followed by a list/explanation

    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
     Google
    0.37
     więc
    0.33
     Sources
    0.33
     ሚ
    0.32
    的是
    0.32
     google
    0.31
     Scenes
    0.30
     pourriez
    0.30
     behavior
    0.30
    ટું
    0.30
    POSITIVE LOGITS
    鸮
    0.31
     পাকিস্ত
    0.30
    Eso
    0.30
    Diameter
    0.29
    NERS
    0.29
    sadquotes
    0.29
     biomark
    0.28
     музея
    0.28
    ടതി
    0.28
     chadd
    0.28
    Activations Density 0.002%

    No Known Activations