© 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. 914
    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
    väl
    1.86
    Item
    1.55
     aloud
    1.52
    ह
    1.52
     அளவுக்கு
    1.51
    ل
    1.50
     От
    1.50
    л
    1.49
    رین
    1.47
     hidrográf
    1.47
    POSITIVE LOGITS
    kannya
    1.98
    şil
    1.71
    เติ
    1.70
    ctions
    1.64
    SLASH
    1.63
    ictive
    1.63
    veh
    1.63
    /−
    1.61
     clarity
    1.61
    localVarHTTP
    1.55
    Activations Density 0.109%

    No Known Activations