© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2254
    Prev
    Next
    INDEX
    Explanations

    words that begin with "tre," often in a technical or medical context.

    oai_token-act-pair · gemini-2.0-flash

    occurrences of 'Tre'

    np_token-act-pair-logits · gpt-4o-mini

    Tre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     snippetHide
    -0.67
    gnal
    -0.62
    yargs
    -0.51
    <bos>
    -0.50
    freie
    -0.50
     hipo
    -0.49
     Aufgabe
    -0.49
    Jäh
    -0.49
    ्यालय
    -0.48
    remia
    -0.47
    POSITIVE LOGITS
    ViewImports
    0.64
     pinulongan
    0.61
     ddelweddau
    0.55
     CreateTagHelper
    0.54
     Seeder
    0.53
    })`
    0.52
    --)
    0.52
    RenderAtEndOf
    0.51
    ẵng
    0.51
    ++]
    0.51
    Activations Density 0.321%

    No Known Activations