© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165742
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     Seniors
    0.39
     Robots
    0.38
    ඟ
    0.37
     Early
    0.36
    뜨
    0.36
     Mansion
    0.36
     décrite
    0.36
    动
    0.35
     Blank
    0.35
    ংকর
    0.35
    POSITIVE LOGITS
    ავი
    0.39
     അവിടെ
    0.35
    ículo
    0.34
    特斯拉
    0.34
    clamp
    0.33
    不必
    0.33
    ánicas
    0.33
     ajan
    0.33
    公安
    0.33
     psychological
    0.33
    Activations Density 0.000%

    No Known Activations