© 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. 3471
    Prev
    Next
    INDEX
    Explanations

    collocations of words related to sports teams and ranking

    oai_token-act-pair · gemini-2.0-flash

    Truncated text 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
    mlung
    -0.50
     '*')
    -0.45
    ("*");
    -0.44
     mê
    -0.42
    loed
    -0.42
    inoza
    -0.42
     spread
    -0.41
    해
    -0.41
    ]={
    -0.41
    jeo
    -0.40
    POSITIVE LOGITS
    NameInMap
    0.77
    modelBuilder
    0.60
     raisonnable
    0.60
    فایل‌لار
    0.58
     mediana
    0.58
    Naissance
    0.56
    enterOuterAlt
    0.56
     vVar
    0.55
    ordano
    0.55
     druga
    0.55
    Activations Density 7.283%

    No Known Activations