© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 6047
    Prev
    Next
    INDEX
    Explanations

    people / gente / gens

    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_3_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
    ن
    2.44
     руководитель
    2.35
     comprennent
    2.33
    o
    2.10
    já
    2.10
    }$
    2.06
    Ironically
    2.05
    ড়াল
    2.02
    elliptic
    2.01
    म्मीद
    1.97
    POSITIVE LOGITS
     smugglers
    2.85
     setState
    2.54
    $('.
    2.43
     utterances
    2.39
     wayside
    2.37
    pygame
    2.28
     smugg
    2.27
    aniyati
    2.21
     посетить
    2.16
     useState
    2.15
    Activations Density 0.045%

    No Known Activations