© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4418
    Prev
    Next
    INDEX
    Explanations

    require/from import

    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_39_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
     chama
    0.40
     Prussians
    0.38
    羍
    0.37
    ່ຽ
    0.37
     dokt
    0.36
    GUID
    0.36
     Chama
    0.36
    ეფ
    0.35
    /////////////
    0.35
     demos
    0.35
    POSITIVE LOGITS
     pro
    0.41
     paper
    0.38
    腐
    0.38
     spoof
    0.38
     counter
    0.38
     corruption
    0.38
     Paper
    0.37
     corrupt
    0.37
    ihn
    0.36
    ='./
    0.36
    Activations Density 0.001%

    No Known Activations