© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6723
    Prev
    Next
    INDEX
    Explanations

    financial groups and conglomerates

    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_40_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
    PathDirectory
    0.41
     שב
    0.40
    🫂
    0.39
    Eisen
    0.39
    饶
    0.39
    oulis
    0.39
    вери
    0.37
    الحمد
    0.37
    երի
    0.36
    ட்டான
    0.36
    POSITIVE LOGITS
    ︎
    0.39
     मानदंड
    0.38
     Normally
    0.38
     Cons
    0.37
     Văn
    0.36
    কিং
    0.36
     kons
    0.36
     drags
    0.36
     Journal
    0.35
     Individual
    0.35
    Activations Density 0.008%

    No Known Activations