© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257908
    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
    야
    0.45
     senso
    0.45
     с
    0.43
     suing
    0.42
    ributor
    0.41
     relying
    0.41
     usp
    0.41
     wagering
    0.41
     anyway
    0.41
     pdb
    0.41
    POSITIVE LOGITS
    চ্য
    0.48
    Criterion
    0.47
    বেশী
    0.46
     Ejecutivo
    0.45
    فت
    0.44
     নৃ
    0.43
    ')){
    0.43
    Bij
    0.43
     demonstra
    0.42
     Calvary
    0.42
    Activations Density 0.000%

    No Known Activations