© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43040
    Prev
    Next
    INDEX
    Explanations

    triple A

    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_13_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
    ök
    0.35
    au
    0.33
     ئى
    0.31
     r
    0.30
     ကြ
    0.30
    jø
    0.30
     ܐ
    0.29
    "，
    0.29
     〢
    0.29
    ø
    0.28
    POSITIVE LOGITS
     city
    0.31
     cidade
    0.30
    视
    0.30
    Си
    0.29
    絘
    0.29
     dashed
    0.29
     concre
    0.29
    の一部
    0.28
     divination
    0.28
     payroll
    0.28
    Activations Density 0.001%

    No Known Activations