© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60420
    Prev
    Next
    INDEX
    Explanations

    Kevin De Bruyne, Kevin Phillips, Torres

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Stationary
    0.54
    장에
    0.54
    라
    0.53
    ธุรกิจ
    0.52
     empres
    0.50
     Sardinia
    0.50
     Ravenna
    0.50
    をする
    0.50
     Trinidad
    0.50
     abate
    0.50
    POSITIVE LOGITS
    M
    0.60
     çal
    0.59
    V
    0.58
     uml
    0.57
    ivre
    0.57
    G
    0.55
    W
    0.54
    libraries
    0.53
    avras
    0.53
     ArrayRef
    0.53
    Activations Density 0.000%

    No Known Activations