© 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. 6610
    Prev
    Next
    INDEX
    Explanations

    speech directives for devices or actions

    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
    technik
    0.44
    棫
    0.41
    Fiction
    0.41
    াউন
    0.39
    Peace
    0.39
    Fols
    0.38
    technology
    0.38
    Machines
    0.38
     પોલીસે
    0.38
     invested
    0.38
    POSITIVE LOGITS
    日常
    0.39
    瑕
    0.38
     소개
    0.37
    |^
    0.37
    妝
    0.37
     tid
    0.36
     exquisite
    0.36
     outgoing
    0.36
    館
    0.36
    怀
    0.36
    Activations Density 0.023%

    No Known Activations