© 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. 1100
    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
    1.13
    𝐢
    0.94
    𝐧
    0.93
    𝐚
    0.89
    𝐥
    0.87
    𝐠
    0.86
     andar
    0.84
    𝐩
    0.84
    𝐓
    0.83
    dır
    0.83
    POSITIVE LOGITS
    в
    1.09
    en
    0.94
    కి
    0.91
    й
    0.86
    ル
    0.85
     precious
    0.83
    ち
    0.81
    ל
    0.78
    ন
    0.78
    ду
    0.77
    Activations Density 0.000%

    No Known Activations