© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79029
    Prev
    Next
    INDEX
    Explanations

    css properties for styling UI elements

    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
     studied
    0.31
    섣
    0.30
     tenang
    0.29
     проблеми
    0.29
     Charger
    0.28
     нюан
    0.28
    葷
    0.28
    ಧಾರವಾಡ
    0.28
     நான்
    0.27
     قسم
    0.27
    POSITIVE LOGITS
    ETHOD
    0.32
    sequ
    0.31
    狎
    0.31
     αί
    0.30
     gráf
    0.30
    queda
    0.30
    Amounts
    0.29
    KEL
    0.29
    Graphical
    0.29
    த்தோ
    0.29
    Activations Density 0.005%

    No Known Activations