© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1907
    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
    ate
    1.24
    i
    1.13
    на
    1.11
    ya
    1.07
     বটে
    1.05
    ll
    1.04
     drawSprites
    1.04
     darn
    1.03
    n
    1.03
    ية
    1.03
    POSITIVE LOGITS
    дың
    1.38
    НЯ
    1.27
     obbl
    1.26
    
    1.22
     ego
    1.22
     желе
    1.21
    ına
    1.21
     esperti
    1.19
     fora
    1.18
     hypergeometric
    1.18
    Activations Density 0.001%

    No Known Activations