© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3371
    Prev
    Next
    INDEX
    Explanations

    business, industry, and enterprise contexts

    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
     Первый
    0.28
    瑶
    0.28
     Asociación
    0.27
     animados
    0.27
    旛
    0.27
     undulating
    0.27
     آنچه
    0.27
     Egipto
    0.26
    _{+}+
    0.26
     acompañada
    0.26
    POSITIVE LOGITS
    Demand
    0.26
    Level
    0.24
    Head
    0.24
    Work
    0.24
    Change
    0.22
    Back
    0.22
    Hard
    0.22
    Unt
    0.21
    Use
    0.21
    level
    0.21
    Activations Density 0.693%

    No Known Activations