© 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-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14456
    Prev
    Next
    INDEX
    Explanations

    terms and names specific to application development, laws, science, and file sharing.

    oai_token-act-pair · gemini-2.0-flash

    storage capacity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terang
    -0.45
     w
    -0.41
    ginfo
    -0.40
     bas
    -0.39
     v
    -0.39
    θει
    -0.38
    Ligações
    -0.38
     found
    -0.37
     mad
    -0.37
     برا
    -0.37
    POSITIVE LOGITS
     AssemblyTitle
    0.77
     GenerationType
    0.74
    AutoScale
    0.73
    .*")]
    0.73
     disambiguazione
    0.70
     NSCoder
    0.69
    mybatisplus
    0.69
    TabIndex
    0.68
     مشين
    0.68
     HasFactory
    0.67
    Activations Density 15.178%

    No Known Activations