© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    defining or describing terms

    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
    Denote
    0.22
     dirinya
    0.21
     diri
    0.21
     владе
    0.20
    們
    0.20
     kitty
    0.20
    on
    0.20
     numa
    0.20
    inputs
    0.20
    াং
    0.20
    POSITIVE LOGITS
    ﻲ
    0.23
     Investigación
    0.23
    भूति
    0.22
    
    0.22
    hetical
    0.22
     화학
    0.22
     Комп
    0.22
    шое
    0.22
     전기
    0.21
    iają
    0.21
    Activations Density 1.597%

    No Known Activations