© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219176
    Prev
    Next
    INDEX
    Explanations

    document loaders

    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
     Ste
    0.40
    ﾊ
    0.38
    πα
    0.37
    Ste
    0.36
    ipso
    0.36
    Brid
    0.36
     Reck
    0.34
    霎
    0.34
     OTA
    0.34
    kara
    0.34
    POSITIVE LOGITS
     documento
    0.53
     documentos
    0.52
     문서
    0.49
     document
    0.49
     Document
    0.48
     документ
    0.47
     DOCUMENT
    0.47
    ocument
    0.46
     dokumen
    0.46
    文档
    0.45
    Activations Density 0.001%

    No Known Activations