© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14791
    Prev
    Next
    INDEX
    Explanations

    querying database performance

    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_13_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
    ad
    0.36
    al
    0.29
    ot
    0.28
     about
    0.28
     về
    0.28
    a
    0.28
     acerca
    0.27
    ان
    0.26
    mış
    0.26
                                
    0.26
    POSITIVE LOGITS
     Datenbank
    0.38
     embryos
    0.34
    Hval
    0.32
    瑋
    0.31
    ✚
    0.31
     yöntem
    0.31
     зобра
    0.30
    𝜌
    0.30
     জাহাজ
    0.30
     Shipbuilding
    0.29
    Activations Density 0.020%

    No Known Activations