© 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. 219751
    Prev
    Next
    INDEX
    Explanations

    performance evaluation statistics

    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
    jarah
    0.42
     kore
    0.41
    iyê
    0.40
    ᱼ
    0.39
    ອບ
    0.38
    matplotlib
    0.38
    阑
    0.37
    noodles
    0.37
     fondée
    0.36
     মণ
    0.36
    POSITIVE LOGITS
     evaluation
    0.39
     cumulative
    0.37
    йна
    0.36
     aggregated
    0.35
    :&
    0.34
     adverse
    0.34
    Evaluation
    0.34
    හර
    0.34
    Probit
    0.34
    Jon
    0.33
    Activations Density 0.000%

    No Known Activations