© 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. 3569
    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
    ות
    2.47
    𝗶
    2.26
     όπως
    2.05
    ्स
    2.04
    𝖙
    2.00
    aan
    1.99
    𝙩
    1.97
    𝘂
    1.97
    Ρ
    1.96
    Πα
    1.96
    POSITIVE LOGITS
    ק
    2.27
    UpInside
    2.19
    કમ
    2.09
     ashes
    1.99
    е
    1.98
     Deserialize
    1.97
    मा
    1.95
    }(
    1.91
     curved
    1.90
    на
    1.90
    Activations Density 0.003%

    No Known Activations