© 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. 245178
    Prev
    Next
    INDEX
    Explanations

    pre-booked airport transfers

    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
     лицен
    0.44
     airplane
    0.41
    boat
    0.41
     boats
    0.41
    easy
    0.41
    econom
    0.39
     airplanes
    0.39
    易
    0.36
     దీంతో
    0.36
    কট
    0.36
    POSITIVE LOGITS
     channel
    0.46
     pre
    0.41
     printing
    0.41
     saved
    0.41
     দফা
    0.40
     included
    0.40
     membeli
    0.40
    購入
    0.40
     executing
    0.40
     Channel
    0.40
    Activations Density 0.003%

    No Known Activations