© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1082
    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
    ive
    1.15
    िव
    1.12
    al
    1.11
    ่
    1.10
    fprintf
    1.08
    nya
    1.07
    िस
    1.05
     ogen
    1.05
    сно
    1.03
    ised
    1.01
    POSITIVE LOGITS
    м
    1.63
     যদি
    1.38
    𝙧
    1.35
     sapiens
    1.31
    
    1.30
    ază
    1.30
     laboris
    1.23
     डैश
    1.23
    ٥
    1.23
    𝙮
    1.22
    Activations Density 0.777%

    No Known Activations