© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16062
    Prev
    Next
    INDEX
    Explanations

    the word "dual"

    oai_token-act-pair · gemini-2.0-flash

    dual

    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
    LookAnd
    -1.00
     <=",
    -0.99
    новниш
    -0.94
     nakalista
    -0.92
    <bos>
    -0.92
     disambiguazione
    -0.91
    MessageOf
    -0.86
     ModelExpression
    -0.84
    Portail
    -0.82
    TagMode
    -0.82
    POSITIVE LOGITS
     cardia
    0.54
     solches
    0.54
    ELES
    0.52
    AtPosition
    0.49
     بيها
    0.48
    ETTI
    0.48
    onger
    0.47
    𝒌
    0.47
     soon
    0.47
     whole
    0.47
    Activations Density 0.840%

    No Known Activations