© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80362
    Prev
    Next
    INDEX
    Explanations

    vehicle accidents

    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_31_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
    orini
    0.38
     ensue
    0.36
    raquinone
    0.36
     grieve
    0.35
    ᱯ
    0.35
     ঘটনার
    0.35
    renergic
    0.35
     mutilated
    0.35
     मेहंदी
    0.34
    け
    0.34
    POSITIVE LOGITS
    Uk
    0.43
     उद
    0.40
    avasena
    0.39
     Uk
    0.38
     Crypt
    0.38
     veniam
    0.38
     alternating
    0.38
    Diamond
    0.37
    Up
    0.37
     Diaz
    0.37
    Activations Density 0.001%

    No Known Activations