© 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. 259493
    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
     as
    0.59
     himself
    0.59
     time
    0.58
    im
    0.57
     auto
    0.57
     path
    0.57
     s
    0.56
     purple
    0.54
     immediately
    0.54
     very
    0.53
    POSITIVE LOGITS
    BBC
    0.56
    BRAS
    0.49
    AFS
    0.46
    OSS
    0.45
     expts
    0.44
     Financing
    0.43
     semanal
    0.43
    Ŵ
    0.43
    会社
    0.42
     carbono
    0.42
    Activations Density 0.000%

    No Known Activations