© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 242027
    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_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
    చి
    0.38
    totalSupply
    0.38
    খী
    0.36
    staben
    0.36
    軐
    0.36
     Agree
    0.35
     Annot
    0.34
     શરી
    0.34
    养
    0.34
    HttpMethod
    0.33
    POSITIVE LOGITS
     Patrick
    0.43
    patrick
    0.42
     incom
    0.41
     recursion
    0.39
    recursive
    0.38
     OU
    0.38
     оди
    0.38
     recurs
    0.37
    Patrick
    0.37
    _="
    0.37
    Activations Density 0.004%

    No Known Activations