© 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. 775
    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
    да
    2.34
    at
    2.27
    ת
    2.17
    um
    2.16
    ן
    2.09
    дів
    2.03
    uat
    1.99
    Основные
    1.98
    bare
    1.97
    Ка
    1.92
    POSITIVE LOGITS
    স্থানীয়
    3.81
    স্থানীয়
    2.96
     earners
    2.87
    soil
    2.53
    𝐩
    2.48
     quarks
    2.43
    ن
    2.40
     notch
    2.36
    riss
    2.35
    nje
    2.34
    Activations Density 0.183%

    No Known Activations