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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5468
    Prev
    Next
    INDEX
    Explanations

    describing states of being

    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
    Вот
    1.55
    ll
    1.55
    nt
    1.36
    rt
    1.30
    Whatever
    1.30
    Жен
    1.28
    da
    1.27
    भ
    1.26
    me
    1.24
    st
    1.23
    POSITIVE LOGITS
    ت
    1.92
    ী
    1.83
    ीन
    1.61
    JlcG
    1.60
    нца
    1.57
    TION
    1.55
    ുടെ
    1.51
    י
    1.50
    ার
    1.49
    이
    1.49
    Activations Density 0.024%

    No Known Activations