© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13515
    Prev
    Next
    INDEX
    Explanations

    code snippets, focusing on particular keywords like "React", "ajax", "DOM", "View", "Request", and "conditional."

    oai_token-act-pair · gemini-2.0-flash

    Code and programming context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ingt
    -0.44
     Tiro
    -0.42
    gerne
    -0.40
    textTheme
    -0.40
    FromArgb
    -0.39
     Ти
    -0.39
     PF
    -0.38
    tabular
    -0.38
    flexDirection
    -0.38
    당
    -0.38
    POSITIVE LOGITS
    AndEndTag
    0.82
    __':
    0.70
    存于互联网档案馆
    0.70
    RUnlock
    0.68
     AssemblyCulture
    0.67
     betweenstory
    0.65
     CURIAM
    0.62
    setopt
    0.62
    principalTable
    0.62
    __':
    0.61
    Activations Density 2.393%

    No Known Activations