© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8038
    Prev
    Next
    INDEX
    Explanations

    know, knows, saber, ว่า

    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
    رت
    2.71
     isEqual
    2.67
    <0x80>
    2.55
    ुक्त
    2.51
    ный
    2.48
    
    2.47
     arma
    2.45
    Shader
    2.44
    ból
    2.41
    n
    2.41
    POSITIVE LOGITS
    这意味着
    2.83
    是
    2.66
    悉
    2.45
    สึก
    2.44
     pasti
    2.38
    ח
    2.33
    ​​​​
    2.32
    chocolate
    2.31
    ោះស្រាយ
    2.29
    晓
    2.29
    Activations Density 0.065%

    No Known Activations