© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3275
    Prev
    Next
    INDEX
    Explanations

    utility functions

    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_5_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
    pictured
    1.03
    𝐚
    0.97
     satiety
    0.97
    𝐦
    0.95
    an
    0.95
    𝐫
    0.95
    𝐛
    0.95
    𝐭
    0.94
    ilevel
    0.93
    𝐯
    0.90
    POSITIVE LOGITS
    larni
    1.10
    esimo
    0.98
    也
    0.88
    dling
    0.88
    та
    0.88
    pent
    0.88
    е
    0.87
     счита
    0.85
    <0xD9>
    0.85
     тысяч
    0.85
    Activations Density 0.005%

    No Known Activations