© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7949
    Prev
    Next
    INDEX
    Explanations

    the word "this" followed by a noun

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AttributeSet
    -0.77
    AxisAlignment
    -0.70
    ChildScrollView
    -0.69
     >=",
    -0.66
    AddHtmlAttribute
    -0.65
     BoxFit
    -0.64
    ArgsConstructor
    -0.64
     BoxDecoration
    -0.63
    />";
    -0.62
     defStyleAttr
    -0.61
    POSITIVE LOGITS
    <bos>
    0.85
     Púb
    0.65
    OGND
    0.57
     ویکی‌پدیای
    0.53
    Dear
    0.52
     felony
    0.49
     Públicas
    0.47
     underlying
    0.47
    HandleFunc
    0.47
     costes
    0.46
    Activations Density 0.373%

    No Known Activations