© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1839
    Prev
    Next
    INDEX
    Explanations

    the word "the" and words that often precede or follow it, such as "more", "less", "much", and forms of "to be".

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     <
    -0.99
    <
    -0.93
    </
    -0.81
    <h1>
    -0.78
    }<
    -0.75
    :<
    -0.68
    "><
    -0.66
     </
    -0.66
    <h2>
    -0.66
     (<
    -0.66
    POSITIVE LOGITS
    RegressionTest
    0.74
    новниш
    0.73
    =$?
    0.72
    InstanceState
    0.71
    出版年
    0.68
    ThroughAttribute
    0.68
    verwijspagina
    0.68
    IndentedString
    0.67
     FetchType
    0.65
    ymce
    0.64
    Activations Density 0.834%

    No Known Activations