© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46862
    Prev
    Next
    INDEX
    Explanations

    level playing field

    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_13_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
    ագր
    0.39
     ,[
    0.38
     sabbam
    0.38
    G
    0.38
     Junior
    0.37
     Months
    0.37
     harem
    0.37
     perished
    0.36
     indignation
    0.36
    󠁮
    0.36
    POSITIVE LOGITS
    était
    0.47
    ListName
    0.45
     их
    0.45
    τής
    0.44
    ປ
    0.44
    ولو
    0.43
     ຫຼື
    0.43
    라고
    0.42
    роў
    0.42
    רוב
    0.42
    Activations Density 0.042%

    No Known Activations