© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6856
    Prev
    Next
    INDEX
    Explanations

    lines that are comments with @ symbols and certain keywords in code

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ngdoc
    -0.50
    portál
    -0.43
    Parcelize
    -0.40
     )
    -0.39
    gida
    -0.39
    subpackage
    -0.38
    asants
    -0.38
    ValueGeneration
    -0.37
    </caption>
    -0.36
    Населення
    -0.36
    POSITIVE LOGITS
     متعلقه
    0.67
    Chham
    0.63
    مصادر
    0.59
    eqn
    0.58
    fällig
    0.57
     Raising
    0.57
    IMPORTED
    0.56
     disambiguazione
    0.56
    ρόν
    0.56
     Rais
    0.55
    Activations Density 1.492%

    No Known Activations