© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97351
    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_14_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
    ut
    0.45
     ⿰
    0.44
     SAME
    0.44
    ud
    0.43
     Verdi
    0.43
    ides
    0.43
    av
    0.43
    ktion
    0.43
    entine
    0.43
     Vladimir
    0.43
    POSITIVE LOGITS
     Komponenten
    0.57
    PlatformToolset
    0.55
     мне
    0.54
    из
    0.52
     силу
    0.52
    ↵
    0.52
    Framework
    0.52
    Feature
    0.51
     рее
    0.51
     понять
    0.50
    Activations Density 0.000%

    No Known Activations