© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110734
    Prev
    Next
    INDEX
    Explanations

    German words with 'urt' or 'urst'

    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_2_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
    :
    1.47
     of
    1.41
    kort
    1.23
    ként
    1.20
    sproz
    1.10
     was
    1.08
    teile
    1.06
     OF
    1.04
    )
    1.02
    ico
    0.99
    POSITIVE LOGITS
    ل
    1.69
    ت
    1.55
    ０
    1.42
    স
    1.29
    ר
    1.29
    ת
    1.27
    л
    1.23
    ש
    1.20
    ین
    1.19
    по
    1.19
    Activations Density 0.000%

    No Known Activations