© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8113
    Prev
    Next
    INDEX
    Explanations

    century or percentage

    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
    kick
    2.94
     hundred
    2.80
    ுகள்
    2.68
    ০০০
    2.68
    篦
    2.66
     podido
    2.55
    ◾
    2.55
    anity
    2.53
    ੱਖ
    2.51
    atás
    2.51
    POSITIVE LOGITS
     moot
    2.86
     spree
    2.60
    ेक
    2.51
    न
    2.50
    ियों
    2.50
    년대
    2.47
     linearized
    2.43
     unge
    2.42
     nei
    2.41
     quadrat
    2.38
    Activations Density 0.147%

    No Known Activations