© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259667
    Prev
    Next
    INDEX
    Explanations

    puncuation followed by new sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    ı
    1.18
     Aufmerksamkeit
    1.17
     సార
    1.12
    ie
    1.11
    Ꮤ
    1.06
    加え
    1.04
    fähigkeit
    1.03
    Ministry
    1.01
    Ƅ
    1.01
    ybės
    1.01
    POSITIVE LOGITS
    மானு
    1.25
     marches
    1.24
     совсем
    1.20
     livre
    1.20
     способов
    1.19
    vä
    1.18
    accordo
    1.15
     trillions
    1.15
     чисел
    1.14
     ridurre
    1.14
    Activations Density 0.000%

    No Known Activations