© 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. 15849
    Prev
    Next
    INDEX
    Explanations

    model code block delimiter

    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
    MRP
    0.38
    min
    0.36
    .):
    0.35
    sei
    0.34
    이야
    0.34
     unrecognizable
    0.34
     insp
    0.34
    Bye
    0.34
    bypass
    0.34
     kel
    0.34
    POSITIVE LOGITS
    য়েক
    0.39
     Mathis
    0.39
    Meat
    0.39
    $('#
    0.38
     }]);
    0.38
     Mies
    0.38
     ([[
    0.38
    的比
    0.38
    akis
    0.37
    кульп
    0.36
    Activations Density 0.029%

    No Known Activations