© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2659
    Prev
    Next
    INDEX
    Explanations

    tools and implements

    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_38_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
    <0x8B>
    0.41
    čil
    0.41
    čení
    0.39
     maus
    0.37
     স্থান
    0.37
     дал
    0.36
    SetStr
    0.36
     episodic
    0.36
    餐廳
    0.35
    聘
    0.35
    POSITIVE LOGITS
     slic
    0.58
     splic
    0.56
     cutter
    0.53
     crusher
    0.51
     splitter
    0.51
     vacuum
    0.50
     balancer
    0.48
     suction
    0.47
     trimmer
    0.47
    uploader
    0.47
    Activations Density 0.095%

    No Known Activations