© 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. 6051
    Prev
    Next
    INDEX
    Explanations

    Lao Tzu or Laos

    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
    isierung
    3.06
    Olá
    2.91
    ⎣
    2.71
    يں
    2.64
    Personendaten
    2.56
     Đó
    2.47
    리는
    2.46
    Cancellation
    2.45
     Nationalist
    2.35
     atvej
    2.35
    POSITIVE LOGITS
    $("#
    2.85
     поча
    2.81
    撾
    2.74
     pública
    2.70
    龵
    2.63
    nex
    2.63
    त
    2.54
    ρά
    2.46
    w
    2.45
    😂😂
    2.45
    Activations Density 0.017%

    No Known Activations