© 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. 2779
    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
    𝙚
    2.07
    не
    1.82
     Invisalign
    1.69
    𝙞
    1.66
    రిత్ర
    1.61
    weds
    1.59
    Defendants
    1.58
    ㅎ
    1.56
    ⺌
    1.55
    ని
    1.53
    POSITIVE LOGITS
    на
    1.93
    зы
    1.74
    pose
    1.63
    isinde
    1.57
    eep
    1.55
     relazione
    1.52
    k
    1.51
    RIO
    1.50
    程度上
    1.48
    าล
    1.45
    Activations Density 0.008%

    No Known Activations