© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151566
    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_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
    FBSDKAppEvents
    0.44
    情况下
    0.42
    Vive
    0.42
    瑣
    0.41
    accommodation
    0.40
     Vive
    0.39
    க்
    0.39
     સમસ્યા
    0.39
    tox
    0.38
    man
    0.38
    POSITIVE LOGITS
     isoforms
    0.43
     ওরফে
    0.42
     correlated
    0.41
    Ѳ
    0.41
     isoform
    0.40
     (−
    0.40
     OMC
    0.40
     derivatives
    0.39
    
    0.39
     clickable
    0.39
    Activations Density 0.000%

    No Known Activations