© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5721
    Prev
    Next
    INDEX
    Explanations

    OneDrive or add to collection

    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_40_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
    hang
    0.44
     الأخيرة
    0.41
     Auf
    0.40
     Real
    0.39
    실
    0.38
    voi
    0.38
    nei
    0.37
    <(),
    0.37
    ுமா
    0.37
    hanger
    0.37
    POSITIVE LOGITS
    Escolhido
    0.40
     Provisional
    0.39
    UIC
    0.39
     پک
    0.38
    User
    0.38
     posti
    0.37
    тт
    0.36
     lud
    0.36
    Pictures
    0.36
    Post
    0.35
    Activations Density 0.055%

    No Known Activations