© 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. 3045
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns

    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
     lẻ
    0.61
    đi
    0.61
    çok
    0.59
    গ
    0.58
     धरा
    0.57
     pretence
    0.57
     misconduct
    0.57
    grav
    0.57
    ตัว
    0.56
    ities
    0.55
    POSITIVE LOGITS
    atically
    0.70
    𝖑
    0.63
    வற்றை
    0.62
    𝖊
    0.62
    𝒓
    0.61
     tecnico
    0.60
     nitride
    0.59
     cualidades
    0.59
    𝒐
    0.59
    𝒔
    0.59
    Activations Density 0.003%

    No Known Activations