© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11545
    Prev
    Next
    INDEX
    Explanations

    the word "away" and words related to leaving

    oai_token-act-pair · gemini-2.0-flash

    away/home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     дописавши
    -0.83
    tagHelperRunner
    -0.75
     AspNetCore
    -0.73
    ifon
    -0.73
    XmlAccessorType
    -0.70
     لينك
    -0.69
     оригіналу
    -0.68
    Архівовано
    -0.67
     AssemblyCulture
    -0.66
    AccessFile
    -0.66
    POSITIVE LOGITS
     Signalez
    0.56
    return
    0.43
    "
    0.43
    .
    0.42
     yılı
    0.42
     sobres
    0.42
    WithIOException
    0.42
     return
    0.41
     vuoden
    0.41
    stoffe
    0.40
    Activations Density 1.383%

    No Known Activations