© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6195
    Prev
    Next
    INDEX
    Explanations

    run and save

    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_39_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
     Bind
    0.41
     lifting
    0.39
     Нау
    0.39
    諮
    0.38
     réglementation
    0.38
    rifft
    0.38
     Egi
    0.38
     κου
    0.38
     bod
    0.37
    hift
    0.36
    POSITIVE LOGITS
    uses
    0.40
     principalColumn
    0.39
    tsx
    0.38
    Commission
    0.38
    Producer
    0.37
    date
    0.37
    韵
    0.37
    ReadAll
    0.36
    鄢
    0.36
    David
    0.36
    Activations Density 0.004%

    No Known Activations