© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215771
    Prev
    Next
    INDEX
    Explanations

    turbocharger

    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_31_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
     بلند
    0.43
     ENGINEERS
    0.39
     ppm
    0.38
    ppm
    0.38
     ppb
    0.38
     മിക
    0.36
     Expert
    0.36
    捎
    0.36
     testim
    0.35
    设计的
    0.35
    POSITIVE LOGITS
     slows
    0.38
    CQL
    0.38
     forks
    0.38
     Demi
    0.37
     fills
    0.36
     mengisi
    0.35
     Fork
    0.35
     pesto
    0.35
    ழுகு
    0.35
     Dès
    0.34
    Activations Density 0.001%

    No Known Activations