© 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. 2274
    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
     chuva
    2.91
     सिलसिला
    2.76
    𝘼
    2.74
     sostanz
    2.56
     distinct
    2.48
     schimb
    2.46
     उनसे
    2.45
    𝙀
    2.45
    謾
    2.39
    这是
    2.38
    POSITIVE LOGITS
    ان
    3.02
    ような
    2.81
    ות
    2.80
    ع
    2.66
    requestFocus
    2.64
    fullscreen
    2.63
     WordPerfect
    2.62
    eligible
    2.57
    atomic
    2.53
    ين
    2.48
    Activations Density 0.019%

    No Known Activations