© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 628
    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
     następnie
    2.07
    at
    1.90
    на
    1.86
    ो
    1.83
     inzwischen
    1.80
     contador
    1.79
     говорится
    1.69
    in
    1.69
    zelfde
    1.68
     αφού
    1.67
    POSITIVE LOGITS
    YYYY
    2.00
    s
    1.98
    jší
    1.92
    jších
    1.84
    ય
    1.81
    ের
    1.77
    šnje
    1.72
    तमंद
    1.72
    yyyy
    1.71
    jším
    1.70
    Activations Density 0.660%

    No Known Activations