© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15574
    Prev
    Next
    INDEX
    Explanations

    the articles "a" and "the," as well as "our," "both", "any", "its", and "given"

    oai_token-act-pair · gemini-2.0-flash

    articles (a, the)

    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
    DispatchToProps
    -0.79
    ReusableCell
    -0.76
     الفلك
    -0.71
    UIControlState
    -0.68
    NameValuePair
    -0.68
    ViewFeatures
    -0.66
    исленность
    -0.66
    Sinopsis
    -0.66
     }}$}
    -0.66
    NewUrlParser
    -0.65
    POSITIVE LOGITS
    <bos>
    1.55
    <em>
    0.59
     passada
    0.54
     tecnico
    0.54
     pesante
    0.53
    kezik
    0.52
     graphiques
    0.52
     embarazada
    0.52
     enfans
    0.51
     habia
    0.50
    Activations Density 2.959%

    No Known Activations