© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4670
    Prev
    Next
    INDEX
    Explanations

    code-like text, specifically HTML, XML, or code mixed with Chinese characters

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    WriteTagHelper
    -0.84
    
    -0.79
    AndEndTag
    -0.79
     Roskov
    -0.76
    Geplaatst
    -0.74
    openqa
    -0.72
    TagMode
    -0.70
     vôtre
    -0.69
    ScopeManager
    -0.69
    MLLoader
    -0.68
    POSITIVE LOGITS
     Vasquez
    0.34
     Nunn
    0.33
     Banners
    0.33
    u
    0.32
     Vaz
    0.31
     Apparent
    0.31
     Palacios
    0.30
     lesions
    0.30
     laughs
    0.30
     Velas
    0.30
    Activations Density 0.961%

    No Known Activations