© 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. 2392
    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
    at
    2.91
    ת
    2.66
    т
    2.53
    ਤ
    2.50
    事情
    2.45
    л
    2.35
     путь
    2.31
    ০
    2.30
    这是
    2.30
     पालन
    2.30
    POSITIVE LOGITS
    r
    3.27
    rj
    3.17
    ்ட்
    2.89
    ियों
    2.68
    رك
    2.68
    rı
    2.56
    rable
    2.53
     srcset
    2.50
    whom
    2.49
     whom
    2.47
    Activations Density 0.179%

    No Known Activations