© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8954
    Prev
    Next
    INDEX
    Explanations

    large mixing bowl

    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_40_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
     Geträn
    0.38
    ዲ
    0.37
     Hackney
    0.36
    檻
    0.36
     mores
    0.34
     footprint
    0.34
    numberOfRecords
    0.34
     lineColor
    0.33
     ৭৫
    0.33
     திர
    0.33
    POSITIVE LOGITS
     bowl
    0.78
     bowls
    0.77
    bowl
    0.71
    Bowl
    0.71
     Bowl
    0.66
    碗
    0.63
     깊
    0.60
     Bowls
    0.59
     deep
    0.59
    deep
    0.59
    Activations Density 0.054%

    No Known Activations