© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3854
    Prev
    Next
    INDEX
    Explanations

    sibling terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    عية
    0.40
    await
    0.37
    jum
    0.37
    \;\
    0.37
     pools
    0.37
    wares
    0.37
    MRS
    0.36
    炮
    0.36
    HMS
    0.36
     ald
    0.36
    POSITIVE LOGITS
     Pr
    0.68
     Ps
    0.61
    Pr
    0.56
     ভাই
    0.51
     ভাইকে
    0.50
     fratello
    0.50
     irmã
    0.49
     brother
    0.48
     pror
    0.48
     ভাইয়ের
    0.47
    Activations Density 0.016%

    No Known Activations