© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59123
    Prev
    Next
    INDEX
    Explanations

    accidents

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    사
    0.75
     са
    0.51
    사와
    0.49
     sa
    0.47
    sa
    0.45
    Sa
    0.44
    사를
    0.44
     سا
    0.42
    사의
    0.40
    사가
    0.40
    POSITIVE LOGITS
     accident
    2.80
     Accident
    2.31
    accident
    2.25
    事故
    2.11
     Unfall
    1.94
     사고
    1.82
     acidente
    1.82
     accidente
    1.80
     दुर्घटना
    1.71
     দুর্ঘটনা
    1.60
    Activations Density 0.073%

    No Known Activations