© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196925
    Prev
    Next
    INDEX
    Explanations

    Magnetic Recording, Cycle, interesting gameplay, Communication Engineering

    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_15_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
    robe
    0.54
     น้อย
    0.53
    น้อย
    0.53
     Egipto
    0.51
     nebo
    0.48
     přek
    0.48
    ず
    0.47
    婳
    0.47
    iliz
    0.46
    -
    0.46
    POSITIVE LOGITS
    using
    0.51
    arder
    0.50
     आटे
    0.47
    this
    0.47
    麦
    0.46
     긴
    0.45
    omicron
    0.45
     Veteran
    0.45
    welcome
    0.44
     Simulation
    0.44
    Activations Density 0.000%

    No Known Activations