© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15005
    Prev
    Next
    INDEX
    Explanations

    words from the Malay language

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     doigt
    -0.54
    tă
    -0.49
    ecap
    -0.47
     porcelaine
    -0.47
     cuivre
    -0.47
     dîner
    -0.43
    érien
    -0.43
     Privat
    -0.43
     manteau
    -0.42
    dchen
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.80
    antaranya
    0.79
    harapkan
    0.77
    berdayakan
    0.75
    libatkan
    0.75
    hadapi
    0.72
    umumkan
    0.72
    baliknya
    0.71
    wakili
    0.71
    ungkapkan
    0.68
    Activations Density 1.564%

    No Known Activations