© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 87102
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    ާ
    0.43
    رو
    0.41
     statistically
    0.38
    就不
    0.38
    osa
    0.38
     jadi
    0.38
    妈妈
    0.38
     worry
    0.38
     curator
    0.38
     cilia
    0.38
    POSITIVE LOGITS
    ORO
    0.54
    ADING
    0.51
     כל
    0.49
     書い
    0.49
    APOLIS
    0.49
     требуется
    0.49
     ܗ
    0.48
    StarCore
    0.48
    ONTO
    0.48
    ULT
    0.47
    Activations Density 0.000%

    No Known Activations