© 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. 3670
    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
    ق
    0.88
    ity
    0.80
    ard
    0.76
    adays
    0.76
     precipitates
    0.74
    غ
    0.73
    क
    0.72
    ICAL
    0.69
    چ
    0.69
    ский
    0.68
    POSITIVE LOGITS
    𝓼
    0.88
    ﺑ
    0.77
    ları
    0.74
    🤌
    0.74
    هایت
    0.68
    𝓽
    0.67
     ét
    0.67
    ЗИ
    0.67
     existe
    0.66
    ır
    0.66
    Activations Density 0.037%

    No Known Activations