© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259246
    Prev
    Next
    INDEX
    Explanations

    Teacher Information table

    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_22_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
     khen
    0.46
    afood
    0.44
    뮌
    0.43
     comedians
    0.41
     попасть
    0.40
     parip
    0.40
    ólica
    0.39
     vorg
    0.39
     confectionery
    0.38
     Indirect
    0.38
    POSITIVE LOGITS
     поча
    0.39
    श्मा
    0.36
    
    0.35
     πραγμα
    0.32
    だった
    0.32
     በኋላ
    0.32
     تلق
    0.32
    実
    0.31
    平均
    0.31
    락
    0.31
    Activations Density 0.000%

    No Known Activations