© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9986
    Prev
    Next
    INDEX
    Explanations

    code snippets with tags of different languages such as HTML, CSS, etc. including tags, version numbers, and other structural elements of code

    oai_token-act-pair · gemini-2.0-flash

    Code, markup, data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     HasFactory
    -0.88
     computer
    -0.81
     Computer
    -0.78
    computer
    -0.75
    Computer
    -0.75
     professional
    -0.75
    Autoritní
    -0.75
     تضيفلها
    -0.73
    Professional
    -0.72
     GenerationType
    -0.72
    POSITIVE LOGITS
    ratto
    0.48
     TAP
    0.47
     Agra
    0.45
     Carter
    0.44
    Carter
    0.43
     Drapeau
    0.43
     tenor
    0.43
    Selen
    0.42
    kill
    0.42
    viv
    0.41
    Activations Density 2.499%

    No Known Activations