© 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. 1389
    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
     proletariat
    1.16
     във
    1.15
    чита
    1.10
    એ
    1.09
     lek
    1.07
     provenienti
    1.03
    ̥
    1.03
    ون
    1.02
    pyrazin
    1.01
     traduc
    1.01
    POSITIVE LOGITS
    ни
    1.34
    ಲ್ಲಿ
    1.05
     লাগিল
    1.01
     BTW
    0.98
    soever
    0.95
    ämään
    0.94
     mevcut
    0.94
    деги
    0.93
    nesse
    0.92
    SUFF
    0.92
    Activations Density 0.239%

    No Known Activations