© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175569
    Prev
    Next
    INDEX
    Explanations

    "contradictory" or "non-existent"

    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_24_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
    超过
    0.43
    uni
    0.42
     когда
    0.41
     ज़रूरत
    0.40
    璫
    0.39
     удалось
    0.38
     जेव्हा
    0.38
    dbh
    0.38
    িয়াল
    0.38
    в
    0.38
    POSITIVE LOGITS
     Warcraft
    0.43
     Tropic
    0.41
     ease
    0.41
    텝
    0.40
     Guardians
    0.39
     कू
    0.39
     painless
    0.38
     curb
    0.38
    টসম্যান
    0.38
     curbs
    0.38
    Activations Density 0.000%

    No Known Activations