© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44739
    Prev
    Next
    INDEX
    Explanations

    European countries and partners

    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_13_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
     italics
    0.56
    Neg
    0.54
    ，
    0.50
     bits
    0.49
    TEMPERATURE
    0.46
    0
    0.46
    1
    0.46
     increments
    0.45
    力和
    0.45
    Dan
    0.44
    POSITIVE LOGITS
     थ्री
    0.56
    oflav
    0.52
    teria
    0.52
    🄴
    0.52
    <unused1005>
    0.51
    സ്ട
    0.51
     ਨਾਲ
    0.49
    mtrl
    0.49
     노래
    0.49
    સિંહ
    0.49
    Activations Density 0.000%

    No Known Activations