© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221038
    Prev
    Next
    INDEX
    Explanations

    spanish or foreign 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_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
     system
    0.50
     policy
    0.46
    q
    0.45
     org
    0.45
    her
    0.45
    unum
    0.45
     ;
    0.44
     GER
    0.44
     service
    0.44
    pl
    0.43
    POSITIVE LOGITS
    йдз
    0.55
    به
    0.55
    elizmente
    0.52
     ajuda
    0.51
    كي
    0.50
    गीय
    0.50
    ابة
    0.49
    ⇝
    0.49
    ንዳ
    0.48
    Ру
    0.48
    Activations Density 0.000%

    No Known Activations