© 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. 6188
    Prev
    Next
    INDEX
    Explanations

    More Detailed Solid Energetic

    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
    си
    1.54
     remed
    1.53
    𝘵
    1.47
    I
    1.46
    𝘮
    1.40
    ب
    1.35
    ви
    1.33
    𝘯
    1.28
     Increment
    1.26
     чер
    1.26
    POSITIVE LOGITS
    没有
    1.71
    ்களின்
    1.56
    η
    1.52
    т
    1.51
    ação
    1.50
    Polygon
    1.48
     apparaissent
    1.47
    院长
    1.47
    paces
    1.46
    通过
    1.45
    Activations Density 0.005%

    No Known Activations