© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244595
    Prev
    Next
    INDEX
    Explanations

    clr.AddReference

    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_40_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
    獺
    0.42
     musculaire
    0.41
     dropdown
    0.41
     बालकनियां
    0.40
     unheard
    0.40
    hydroxyl
    0.40
     rozwią
    0.40
     tsa
    0.39
     dilap
    0.39
    栃
    0.39
    POSITIVE LOGITS
     Ig
    0.40
     purposes
    0.39
     செய்
    0.39
     platform
    0.37
     Platform
    0.37
     bác
    0.37
    Platform
    0.36
    平台
    0.36
    ผ่น
    0.35
     processes
    0.35
    Activations Density 0.000%

    No Known Activations