© 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. 3325
    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
    ع
    2.46
    sing
    2.45
    suk
    2.39
    на
    2.35
     جهد
    2.30
    والفقار
    2.29
    श्वर
    2.23
    न
    2.21
    之力
    2.18
     sigmoid
    2.18
    POSITIVE LOGITS
     spaced
    2.56
    ]})
    2.55
     attention
    2.45
    𝐫
    2.34
    쏠
    2.31
     minum
    2.21
    ных
    2.20
    attention
    2.15
    ного
    2.13
    ך
    2.09
    Activations Density 0.035%

    No Known Activations