© 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. 3128
    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
    y
    1.56
    ਰ
    1.39
    mà
    1.36
     prés
    1.35
    mäß
    1.34
     zwią
    1.33
    ২৯
    1.33
     alleen
    1.32
    భ
    1.30
    𝑐
    1.28
    POSITIVE LOGITS
    pped
    1.30
    ടും
    1.24
     pitan
    1.20
    你
    1.19
    arrayList
    1.18
    드
    1.17
    ре
    1.16
    ं
    1.14
    ছিলেন
    1.11
    jų
    1.08
    Activations Density 0.010%

    No Known Activations