© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3326
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    𝗿
    3.42
    𝗵
    3.16
    𝗠
    2.89
    𝗲
    2.89
    𝗚
    2.88
    𝗮
    2.86
     fato
    2.85
    𝗶
    2.81
    𝗛
    2.80
    𝗕
    2.77
    POSITIVE LOGITS
    ب
    3.83
    ن
    3.34
    و
    2.90
    ruary
    2.68
    ১
    2.61
    dul
    2.57
    ेक्षित
    2.55
    А
    2.54
    s
    2.47
    న
    2.42
    Activations Density 0.051%

    No Known Activations