© 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
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37080
    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_57_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
    aniti
    0.39
     toJson
    0.38
    부터
    0.38
    він
    0.38
     ನೆ
    0.37
     Moulin
    0.36
    ቑ
    0.36
     至
    0.36
     Bim
    0.36
    充满了
    0.36
    POSITIVE LOGITS
    າດ
    0.45
     recorte
    0.39
     отдыха
    0.38
    herd
    0.37
     Ridley
    0.35
     furrow
    0.35
     honest
    0.34
     arte
    0.34
     техника
    0.34
     direct
    0.34
    Activations Density 0.000%

    No Known Activations