© 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. 2173
    Prev
    Next
    INDEX
    Explanations

    vehicle accidents and damage

    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
     instance
    0.40
     रहना
    0.39
    𝘩
    0.37
    Stay
    0.37
     Instance
    0.37
     Stay
    0.36
     छोटी
    0.35
    hena
    0.35
     stay
    0.34
    Leben
    0.33
    POSITIVE LOGITS
    форд
    0.42
     dãy
    0.37
    VELOP
    0.37
    氟
    0.36
     Washington
    0.35
    osoever
    0.35
    軫
    0.35
     Venezia
    0.35
    Washington
    0.35
    Brist
    0.35
    Activations Density 0.025%

    No Known Activations