© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1680
    Prev
    Next
    INDEX
    Explanations

    phrases that reference scales and the number ten

    oai_token-act-pair · gemini-2.0-flash

    ten

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    oznam
    -0.63
    XmlIgnore
    -0.62
     שוליים
    -0.62
    :]:
    -0.61
    IsContent
    -0.60
    érateur
    -0.58
    apd
    -0.57
    maked
    -0.57
    はじめに
    -0.56
    .~(\
    -0.56
    POSITIVE LOGITS
    StreetMap
    0.50
    AddHtmlAttribute
    0.50
    levels
    0.47
    Level
    0.47
    AndEndTag
    0.46
    ValueStyle
    0.45
    Levels
    0.44
    SourceChecksum
    0.44
    PullParser
    0.44
     gyhoeddwyd
    0.43
    Activations Density 1.163%

    No Known Activations