© 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. 3185
    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
    ontal
    2.40
    ित
    2.35
    сть
    2.33
    𝒶
    2.24
    𝐼
    2.23
     gì
    2.16
    ,:)
    2.12
    ిన
    2.05
    𝑔
    2.02
    ל
    2.02
    POSITIVE LOGITS
    ج
    2.86
     ří
    2.56
    ं
    2.46
    et
    2.42
     arada
    2.41
     choses
    2.38
    上午
    2.34
    પ
    2.31
    下午
    2.29
     clockwise
    2.28
    Activations Density 0.038%

    No Known Activations