© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50500
    Prev
    Next
    INDEX
    Explanations

    list development

    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_30_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
     predecess
    0.44
     tượng
    0.39
     potted
    0.38
     disclosed
    0.38
     Expanded
    0.38
     {}>,
    0.37
     UBC
    0.37
     cal
    0.36
     '+
    0.36
     conoc
    0.36
    POSITIVE LOGITS
    aturally
    0.41
    আমরা
    0.40
    ピオン
    0.40
     আমরা
    0.39
    ancel
    0.39
     naughty
    0.39
    我们会
    0.38
    formance
    0.38
    ukin
    0.38
     बराबरी
    0.37
    Activations Density 0.017%

    No Known Activations