© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138989
    Prev
    Next
    INDEX
    Explanations

    *despite* across languages

    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_37_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
    鱸
    0.37
    rola
    0.36
     shopping
    0.36
     }\
    0.36
     suele
    0.36
     usually
    0.35
     metastable
    0.34
     !}\
    0.34
     !!
    0.34
     eateries
    0.33
    POSITIVE LOGITS
     malgré
    0.54
    despite
    0.54
     despite
    0.54
     সামগ্র
    0.53
     Despite
    0.50
    Despite
    0.50
     spite
    0.49
     رغم
    0.49
     несмотря
    0.43
     trotz
    0.42
    Activations Density 0.000%

    No Known Activations