© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209828
    Prev
    Next
    INDEX
    Explanations

    ingredient likes/dislikes

    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
     refuted
    0.41
     curtailed
    0.39
     camped
    0.38
     diverted
    0.38
     shuffled
    0.37
     resuspended
    0.37
     и
    0.36
     outperformed
    0.36
     swallowed
    0.36
     إلى
    0.36
    POSITIVE LOGITS
    h
    0.48
    c
    0.42
    1
    0.40
    ന
    0.37
    น
    0.34
    Create
    0.34
    த
    0.34
    च
    0.34
    ج
    0.34
    മ
    0.34
    Activations Density 0.012%

    No Known Activations