© 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. 49560
    Prev
    Next
    INDEX
    Explanations

    video games

    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
    🥈
    0.34
    ದೇ
    0.34
    ünden
    0.33
     unrecognizable
    0.32
    Booking
    0.32
    ꯌ
    0.32
    ໍ່
    0.32
    𒌍
    0.32
     ज्
    0.32
    ແ
    0.31
    POSITIVE LOGITS
     whitew
    0.45
     videot
    0.38
     lifted
    0.37
     white
    0.37
     жи
    0.37
     White
    0.37
     lifting
    0.36
     Forecast
    0.36
     Sno
    0.36
    ursed
    0.35
    Activations Density 0.037%

    No Known Activations