© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3360
    Prev
    Next
    INDEX
    Explanations

    shut up

    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
     batsmen
    1.00
    𝘯
    0.90
    所示
    0.85
    ти
    0.84
    不堪
    0.84
     mutual
    0.84
     возникновения
    0.83
    platten
    0.82
    DZ
    0.81
     Gubernur
    0.79
    POSITIVE LOGITS
    お金
    1.00
    一个
    0.94
    espèce
    0.90
    一个新的
    0.89
    ן
    0.88
    oretical
    0.88
    いえ
    0.87
    и
    0.86
    ع
    0.86
     রকমের
    0.85
    Activations Density 0.001%

    No Known Activations