© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172134
    Prev
    Next
    INDEX
    Explanations

    splitting 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_20_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
    🦉
    0.10
     بغ
    0.10
     عدة
    0.10
    이었다
    0.09
    を含む
    0.09
     クリーム
    0.09
    的一個
    0.09
     細胞
    0.09
     several
    0.09
    igem
    0.09
    POSITIVE LOGITS
     proiz
    0.09
     Aqui
    0.09
    W
    0.09
     prikaz
    0.09
    glichen
    0.09
    Aqui
    0.08
     By
    0.08
     charme
    0.08
     granularity
    0.08
     Haga
    0.08
    Activations Density 0.001%

    No Known Activations