© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37764
    Prev
    Next
    INDEX
    Explanations

    local places or features

    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_11_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
    נ
    0.61
    斯特
    0.55
    🌬
    0.55
     creatividad
    0.54
    <0x98>
    0.54
     говорил
    0.54
    ევ
    0.53
    🌍
    0.53
    の中でも
    0.53
    <0x97>
    0.52
    POSITIVE LOGITS
     wn
    0.56
    ak
    0.55
     subpo
    0.54
     wary
    0.54
     locally
    0.53
    ğun
    0.52
     الفور
    0.52
    setLookAndFeel
    0.51
     تمت
    0.51
    a
    0.50
    Activations Density 0.009%

    No Known Activations