© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203345
    Prev
    Next
    INDEX
    Explanations

    **

    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_6_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
    in
    0.99
    ↵
    0.97
    em
    0.97
    šić
    0.95
    da
    0.86
    av
    0.86
     '
    0.84
    zer
    0.84
     hotly
    0.82
    ,'
    0.81
    POSITIVE LOGITS
    ку
    1.23
    िक
    1.13
    ној
    1.05
    т
    1.00
    но
    0.97
    ной
    0.97
    ях
    0.95
    m
    0.95
     eux
    0.93
    ی
    0.93
    Activations Density 0.000%

    No Known Activations