© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1807
    Prev
    Next
    INDEX
    Explanations

    Spanish or Portuguese words and phrases

    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_39_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
     Trail
    0.17
     llamada
    0.15
     graf
    0.15
     ব্যক্তিত্ব
    0.15
     muñ
    0.15
    leg
    0.14
     c
    0.14
     nowadays
    0.14
     hone
    0.14
    λούν
    0.14
    POSITIVE LOGITS
    inationals
    0.16
    veen
    0.16
     }}{\
    0.15
     graduellement
    0.15
    䈤
    0.15
    டம்
    0.14
     bakın
    0.14
     satisfactorily
    0.14
    즌
    0.14
    Ȧ
    0.14
    Activations Density 0.165%

    No Known Activations