© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101083
    Prev
    Next
    INDEX
    Explanations

    public places, bathrooms, and markets

    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_16_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
    mathrm
    0.47
    Workspace
    0.47
    ىل
    0.45
    л
    0.45
    ل
    0.45
    neş
    0.43
    Community
    0.43
    Teachers
    0.43
     sa
    0.42
    ห
    0.42
    POSITIVE LOGITS
     termen
    0.53
     motorway
    0.51
     wolves
    0.50
    ੰਜ
    0.49
     tolls
    0.48
     hipert
    0.48
     malls
    0.48
    फ्त
    0.47
     marshes
    0.47
    럇
    0.47
    Activations Density 0.037%

    No Known Activations