© 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. 79932
    Prev
    Next
    INDEX
    Explanations

    legally placed on the market or new residents

    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
     Emer
    0.40
    Amplitude
    0.35
     hydrol
    0.35
     Maruti
    0.35
     Adj
    0.34
     Ane
    0.34
     inan
    0.34
    ^{[
    0.34
    Emergency
    0.33
    мна
    0.33
    POSITIVE LOGITS
    )>=
    0.52
     ≥
    0.48
    Greater
    0.42
     Greater
    0.42
    forward
    0.40
    大于
    0.40
    超过
    0.38
    小于
    0.37
     irresistible
    0.36
     начиная
    0.36
    Activations Density 0.022%

    No Known Activations