© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1822
    Prev
    Next
    INDEX
    Explanations

    code snippets consisting of variable properties and chart areas

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    eseorang
    -0.54
    racle
    -0.52
    inerja
    -0.51
     financiera
    -0.50
    IntoConstraints
    -0.50
     setDate
    -0.48
    Citiți
    -0.48
     asiática
    -0.48
    pike
    -0.47
    vedades
    -0.47
    POSITIVE LOGITS
    IsContent
    0.87
    consulté
    0.66
     esternos
    0.65
    Geplaatst
    0.60
     consultato
    0.57
    افظة
    0.57
    RenderAtEndOf
    0.57
    WithIOException
    0.56
    Портал
    0.55
     disambiguazione
    0.53
    Activations Density 8.428%

    No Known Activations