© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5694
    Prev
    Next
    INDEX
    Explanations

    accident, vehicle

    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_38_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
    oggle
    0.42
     sixteen
    0.42
    >∈</
    0.39
    oggles
    0.38
     Fifteen
    0.38
    őt
    0.36
     viêm
    0.36
     Alkaline
    0.36
     ontology
    0.36
     eighteen
    0.36
    POSITIVE LOGITS
    랏
    0.46
    accident
    0.44
    事故
    0.43
     accident
    0.42
     accidentes
    0.42
     Unfall
    0.42
     Accident
    0.41
     사고
    0.41
    行驶
    0.40
     rims
    0.38
    Activations Density 0.016%

    No Known Activations