© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38196
    Prev
    Next
    INDEX
    Explanations

    nicht followed by negation or other German words

    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
    es
    0.40
    ad
    0.39
    stvu
    0.38
    ၅
    0.37
    ş
    0.37
    st
    0.36
    bedarf
    0.36
     ομάδα
    0.36
    ၃
    0.36
     Δεν
    0.36
    POSITIVE LOGITS
    ه
    0.40
    a
    0.39
     maya
    0.36
     crayons
    0.35
    ้ง
    0.34
    ה
    0.33
     chang
    0.32
     Ang
    0.32
     paradox
    0.32
     conjug
    0.31
    Activations Density 0.000%

    No Known Activations