© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14992
    Prev
    Next
    INDEX
    Explanations

    stop-and-go driving

    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_15_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
     wszyst
    0.57
    ट
    0.55
    ين
    0.55
    вить
    0.51
    يك
    0.49
    원
    0.49
    टोन
    0.49
     البريط
    0.48
    레
    0.48
     pelea
    0.48
    POSITIVE LOGITS
    umé
    0.52
     genuine
    0.52
    omatic
    0.51
     diving
    0.47
     dogma
    0.47
    shund
    0.47
     eagerness
    0.47
     dog
    0.47
     kindness
    0.47
     shocking
    0.47
    Activations Density 0.002%

    No Known Activations