© 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. 28709
    Prev
    Next
    INDEX
    Explanations

    http followed by packages

    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
    bage
    0.46
     releg
    0.43
    組
    0.42
    インターネット
    0.40
     인터넷
    0.40
    internet
    0.40
     protesting
    0.39
     internet
    0.39
    agliari
    0.39
     इंटरनेट
    0.38
    POSITIVE LOGITS
    箭
    0.42
    Sync
    0.41
     rese
    0.40
    rese
    0.40
    HTTP
    0.39
    籬
    0.38
     erit
    0.37
     Nets
    0.37
     Proven
    0.37
    wed
    0.37
    Activations Density 0.001%

    No Known Activations