© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2931
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_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
    E
    0.28
    S
    0.25
    Correspondence
    0.25
    রূপে
    0.25
    Votre
    0.24
    必要があります
    0.24
    StringBuilder
    0.23
    )=>{
    0.23
    +]
    0.23
    T
    0.23
    POSITIVE LOGITS
    ová
    0.29
     stipulation
    0.28
    hões
    0.27
     vomiting
    0.27
     autorità
    0.27
     galore
    0.27
    owały
    0.26
     equaling
    0.26
     combinação
    0.26
     apel
    0.26
    Activations Density 0.865%

    No Known Activations