© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9823
    Prev
    Next
    INDEX
    Explanations

    latex document setup

    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
     Steady
    0.38
    闯
    0.35
    🟢
    0.35
     एल्गोरि
    0.34
    Steady
    0.34
     Alexis
    0.34
    Alexis
    0.34
     সভাপত
    0.33
    📀
    0.33
     알고
    0.33
    POSITIVE LOGITS
     input
    0.49
    input
    0.46
     Input
    0.40
     Post
    0.39
     post
    0.35
    prises
    0.35
     INPUT
    0.34
    Input
    0.34
    post
    0.33
    list
    0.33
    Activations Density 0.000%

    No Known Activations