© 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. 10178
    Prev
    Next
    INDEX
    Explanations

    the word "scope," sometimes preceded by other words such as "if"

    oai_token-act-pair · gemini-2.0-flash

    scope

    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
     sub
    -0.69
     It
    -0.69
    .
    -0.67
     "
    -0.66
     The
    -0.65
     part
    -0.65
     site
    -0.65
     so
    -0.64
     in
    -0.64
     be
    -0.63
    POSITIVE LOGITS
     дописавши
    1.38
     feroit
    1.14
     nakalista
    1.13
    TagMode
    1.10
     avoient
    1.07
     MenuView
    1.07
     auroit
    1.06
     beginnetje
    1.05
    <bos>
    1.05
    RegressionTest
    1.03
    Activations Density 0.768%

    No Known Activations