© 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. 3755
    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
    ../../
    2.92
    ্র
    2.71
    zum
    2.68
     ime
    2.65
     그러니까
    2.61
    ⓪
    2.59
    SuppressWarnings
    2.54
    en
    2.49
    此
    2.47
    од
    2.46
    POSITIVE LOGITS
     вот
    3.84
    ल
    3.26
     образом
    3.12
    y
    3.10
     प्रकारे
    3.05
     eben
    2.99
    টা
    2.98
    د
    2.98
    𝚜
    2.91
     ώστε
    2.90
    Activations Density 0.010%

    No Known Activations