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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 120
    Prev
    Next
    INDEX
    Explanations

    HTML code, especially related to element attributes, class lists, and DOM manipulation

    oai_token-act-pair · gemini-2.0-flash

    Javascript and HTML 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    //~
    -0.45
    Tos
    -0.41
     Tole
    -0.41
     Luis
    -0.41
    ☆☆☆
    -0.40
    Stmt
    -0.40
    styleType
    -0.39
     destro
    -0.39
    consulté
    -0.38
    ionale
    -0.38
    POSITIVE LOGITS
    DockStyle
    0.91
    IntoConstraints
    0.91
    tvguidetime
    0.84
    pageY
    0.83
    +#+#
    0.82
    makeConstraints
    0.79
    nextElement
    0.79
    WebMethod
    0.79
    clientY
    0.76
    clientWidth
    0.75
    Activations Density 1.861%

    No Known Activations