© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2926
    Prev
    Next
    INDEX
    Explanations

    demands and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ाना
    1.20
    ीय
    1.07
    र
    1.04
    ाइ
    0.98
    其他
    0.98
    ровал
    0.97
    довой
    0.96
    ggbb
    0.96
    ش
    0.96
    く
    0.95
    POSITIVE LOGITS
     hỏi
    1.28
    不高
    1.26
     منك
    1.19
     ogr
    1.13
     pinion
    1.12
     lasci
    1.06
     sanciones
    1.06
     dalších
    1.06
     ο
    1.01
     glory
    1.00
    Activations Density 0.155%

    No Known Activations