© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198852
    Prev
    Next
    INDEX
    Explanations

    ECOG Performance Status Scale

    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_12_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
    私は
    0.50
    ặn
    0.48
    S
    0.47
    钢
    0.46
    分子
    0.46
     timelines
    0.46
     showrooms
    0.45
     n
    0.43
     o
    0.43
    צוני
    0.43
    POSITIVE LOGITS
     Cáceres
    0.49
    យើង
    0.48
     Valenc
    0.47
     Andres
    0.47
    és
    0.46
     Palacio
    0.45
    樫
    0.45
     País
    0.43
    ultz
    0.43
     орган
    0.42
    Activations Density 0.000%

    No Known Activations