© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61520
    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_11_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
     can
    0.50
     ப
    0.50
     Ch
    0.48
     Taylor
    0.48
     world
    0.47
     African
    0.46
     ML
    0.46
     buhay
    0.45
     F
    0.45
     EM
    0.45
    POSITIVE LOGITS
    ('=
    0.58
    BtnPanel
    0.56
    HasFieldError
    0.56
    ('/\
    0.52
    Isopropyl
    0.52
     leftWheel
    0.51
    IllegalArgument
    0.51
    FreeFlag
    0.51
    MaxLength
    0.50
    UpSync
    0.50
    Activations Density 0.000%

    No Known Activations