© 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. 530
    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
     praw
    1.40
    ∈
    1.38
    𝑎
    1.38
    ε
    1.36
     buah
    1.35
    є
    1.30
    ய
    1.30
    sl
    1.29
     consequat
    1.26
    ح
    1.18
    POSITIVE LOGITS
    et
    1.62
    eur
    1.52
    ות
    1.44
    eer
    1.43
    ły
    1.40
    ங்கிணை
    1.39
    ech
    1.38
    يش
    1.37
    ﻱ
    1.34
    𝐧
    1.33
    Activations Density 0.243%

    No Known Activations