© 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
    2. Gemma-3-4B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-16K
    4. 2150
    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_12_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
    𝙶
    0.40
     ความ
    0.39
     น้ำ
    0.37
     Flüss
    0.36
     iş
    0.36
     ஐந்து
    0.35
     bangunan
    0.35
     Seorang
    0.35
    𝑇
    0.35
    यास
    0.35
    POSITIVE LOGITS
     thanked
    0.33
     opted
    0.31
     briefed
    0.30
     =",
    0.30
     included
    0.29
     informed
    0.27
     explained
    0.27
     assured
    0.27
     потен
    0.27
    avia
    0.26
    Activations Density 0.122%

    No Known Activations