© 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. 3558
    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
    ে
    2.56
    ва
    2.48
    eer
    2.42
    ی
    2.35
    e
    2.28
    یہ
    2.24
    eers
    2.20
    ní
    2.17
    یه
    2.16
    lighthouse
    2.15
    POSITIVE LOGITS
    as
    1.94
     Кроме
    1.85
    ından
    1.65
     reste
    1.64
    ese
    1.63
    у
    1.62
     crave
    1.62
    ête
    1.58
     imbalance
    1.57
     convuls
    1.56
    Activations Density 0.008%

    No Known Activations