© 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. 281
    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
    y
    4.01
    𝑦
    3.33
    𝐾
    2.76
    jší
    2.76
     weiß
    2.69
    ła
    2.62
     voilà
    2.61
    य
    2.52
    স্থানীয়
    2.50
     devenir
    2.48
    POSITIVE LOGITS
    त्मक
    3.06
    و
    2.86
    ্যাল
    2.77
    িকাংশ
    2.67
    ला
    2.62
    घव
    2.62
    しまいました
    2.61
    vd
    2.60
     yon
    2.56
    ले
    2.55
    Activations Density 0.055%

    No Known Activations