© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258545
    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_22_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
    🏠
    0.31
    kid
    0.30
    曇
    0.29
     phenotype
    0.27
    VZ
    0.27
     rheumatic
    0.27
    <img>
    0.26
    ⁸
    0.26
     phenotypes
    0.26
    ಕಿ
    0.26
    POSITIVE LOGITS
     Abr
    0.40
    Abr
    0.34
     Wainwright
    0.31
     terci
    0.31
    órd
    0.30
     দুর্দ
    0.29
     Alban
    0.29
     Hercules
    0.29
     Java
    0.29
     fuerte
    0.29
    Activations Density 0.002%

    No Known Activations