© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84378
    Prev
    Next
    INDEX
    Explanations

    visitors into customers

    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_23_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
     자유
    0.42
    navigationItem
    0.41
     苏
    0.39
     свобо
    0.38
    नावश्यक
    0.38
    自由
    0.36
     immunity
    0.36
     wobei
    0.36
     freely
    0.36
     поль
    0.36
    POSITIVE LOGITS
     percentile
    0.43
    東京
    0.42
     	i
    0.40
     PERCENT
    0.40
    urally
    0.39
     Durante
    0.39
     verzi
    0.39
    ipada
    0.39
    
    0.38
     manipulating
    0.38
    Activations Density 0.001%

    No Known Activations