© 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. 36472
    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
    wonderful
    0.55
    CloseOperation
    0.52
    ън
    0.52
    也許
    0.52
    ệt
    0.51
    ன்ஸ்
    0.51
    쐞
    0.51
    𝗻
    0.50
    ⦿
    0.50
     لیګ
    0.49
    POSITIVE LOGITS
     microtub
    0.59
    0.54
     spleen
    0.51
     to
    0.51
     of
    0.50
     voxel
    0.50
    <start_of_image>
    0.50
     tagged
    0.48
     renal
    0.48
     allele
    0.48
    Activations Density 0.000%

    No Known Activations