© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4668
    Prev
    Next
    INDEX
    Explanations

    countries and financial institutions

    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
    y
    0.61
    es
    0.59
    am
    0.55
    бто
    0.52
    pone
    0.48
    day
    0.47
    winning
    0.46
    ed
    0.45
    bs
    0.45
    すすめ
    0.44
    POSITIVE LOGITS
     betrachtet
    0.52
     éto
    0.51
     entityManager
    0.51
     incarcer
    0.50
    ɢ
    0.49
    𝒆
    0.49
    檎
    0.49
     rethink
    0.48
    ʜ
    0.47
     domést
    0.47
    Activations Density 0.306%

    No Known Activations