© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6721
    Prev
    Next
    INDEX
    Explanations

    HTML elements with "form" and possibly "radio", "option", or "item" in their class

    oai_token-act-pair · gemini-2.0-flash

    special characters and HTML/XML tags

    np_token-act-pair-logits · gpt-4o-mini

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ibatis
    -0.49
     fueling
    -0.48
    getBean
    -0.43
    Rails
    -0.43
     subtly
    -0.42
     privatization
    -0.42
     Vib
    -0.42
    ränke
    -0.41
    yscale
    -0.41
     Manly
    -0.40
    POSITIVE LOGITS
     Normdatei
    0.86
    帖最后由
    0.79
     ProtoMessage
    0.72
     esternos
    0.69
    Jîn
    0.68
    الحياه
    0.67
    AnchorTagHelper
    0.63
    findpost
    0.63
    rungsseite
    0.62
    Билгалдахарш
    0.60
    Activations Density 0.411%

    No Known Activations