© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27979
    Prev
    Next
    INDEX
    Explanations

    unless-stopped

    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_10_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
     agitated
    0.27
    o
    0.27
    ad
    0.27
    ain
    0.25
    ozer
    0.25
     будь
    0.24
    あなたが
    0.24
     crucified
    0.23
    λία
    0.23
     unsh
    0.23
    POSITIVE LOGITS
     C
    0.30
     U
    0.28
     R
    0.27
     K
    0.25
     På
    0.25
     I
    0.24
     Ç
    0.23
    Ș
    0.23
    ings
    0.23
     S
    0.23
    Activations Density 0.004%

    No Known Activations