© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100549
    Prev
    Next
    INDEX
    Explanations

    limited liability companies or Spanish 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_16_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
    fullName
    0.54
    ب
    0.52
    ну
    0.47
     producing
    0.46
    ്ട
    0.46
    نی
    0.45
    घ
    0.45
    Bened
    0.45
    primarily
    0.44
     accom
    0.43
    POSITIVE LOGITS
     Pointer
    0.49
     低
    0.47
     Chihuahua
    0.47
     Phantom
    0.47
     contradictions
    0.46
     Sw
    0.46
     angina
    0.46
     seh
    0.45
     Freiburg
    0.45
     polyt
    0.45
    Activations Density 0.000%

    No Known Activations