© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91608
    Prev
    Next
    INDEX
    Explanations

    machine to machine communications

    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_11_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
    ↵↵
    0.43
     coaster
    0.43
    </h2>
    0.41
    RIO
    0.40
     unexpected
    0.39
    LG
    0.39
    2
    0.38
    IL
    0.38
     consecutive
    0.37
    "
    0.37
    POSITIVE LOGITS
    ပြည်
    0.54
     compds
    0.51
     Papua
    0.51
    వ్ర
    0.51
    샨
    0.51
     Pary
    0.50
    ský
    0.49
     Gipps
    0.49
    िष्ट
    0.48
    𝐠
    0.48
    Activations Density 0.054%

    No Known Activations