© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200824
    Prev
    Next
    INDEX
    Explanations

    snorkeling activities and gear

    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_12_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
     Sean
    0.55
     reef
    0.54
    \
    0.54
     Reef
    0.52
    ຕົວ
    0.51
    ệt
    0.50
    шень
    0.49
     Ủy
    0.49
    %">
    0.47
    ançaise
    0.47
    POSITIVE LOGITS
     gamanam
    0.57
    Cort
    0.55
    diagram
    0.53
    inode
    0.52
     aide
    0.52
    ECE
    0.51
    uram
    0.51
    atonin
    0.50
     quinoa
    0.50
    ena
    0.50
    Activations Density 0.004%

    No Known Activations