© 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. 3290
    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
    cknowled
    1.91
    
    1.88
    𝚊
    1.76
     bijection
    1.71
    𝚜
    1.70
     incurred
    1.68
     सिखा
    1.65
     Kõ
    1.64
    𝘄
    1.64
     potuto
    1.63
    POSITIVE LOGITS
    ع
    1.71
    ik
    1.70
    ive
    1.60
     nesses
    1.52
    п
    1.44
    й
    1.40
    iti
    1.36
    spaper
    1.35
    Purs
    1.33
    ok
    1.32
    Activations Density 0.052%

    No Known Activations