© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261292
    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_22_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
    s
    0.54
    ot
    0.45
    ad
    0.43
     horrifying
    0.43
    SearchResults
    0.43
     horrific
    0.43
    大人
    0.42
     disastrous
    0.41
    Dire
    0.41
    قدر
    0.41
    POSITIVE LOGITS
     các
    0.48
     больных
    0.47
     pensamiento
    0.46
     metac
    0.46
     SOA
    0.45
    :+
    0.45
     artic
    0.45
     sépar
    0.45
    ıza
    0.44
     articul
    0.44
    Activations Density 0.000%

    No Known Activations