© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195159
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    माटर
    0.54
    dollar
    0.52
     shatter
    0.50
    unters
    0.50
     shattering
    0.49
     sl
    0.47
    t
    0.47
    ﺜ
    0.47
     revolution
    0.46
     Telugu
    0.46
    POSITIVE LOGITS
     ayant
    0.57
    Den
    0.57
    این
    0.55
    یسم
    0.55
    Denne
    0.53
    ک
    0.53
     প্রায়
    0.49
    Nous
    0.49
    ین
    0.48
    Мы
    0.48
    Activations Density 0.000%

    No Known Activations