© 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. 30617
    Prev
    Next
    INDEX
    Explanations

    bungee jumping

    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
     hotel
    0.42
     Hotel
    0.40
     motel
    0.40
     articul
    0.39
     coronary
    0.39
    Hotel
    0.38
     rattling
    0.38
    园
    0.38
    гази
    0.37
     HOTEL
    0.37
    POSITIVE LOGITS
     tren
    0.39
    पहली
    0.38
     खाई
    0.37
     رفتار
    0.35
     Ranked
    0.34
    iciembre
    0.34
     Ад
    0.34
     Seventy
    0.34
     अध
    0.33
    支付
    0.33
    Activations Density 0.003%

    No Known Activations