© 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. 11266
    Prev
    Next
    INDEX
    Explanations

    root words or word fragments ending in "ude," "ula," "agle," "ist", "ced" or "CI".

    oai_token-act-pair · 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
    Portail
    -0.66
    <bos>
    -0.64
    AddHtmlAttribute
    -0.58
     kasarigan
    -0.56
     ModelRenderer
    -0.55
    bete
    -0.54
    Submitting
    -0.54
    new
    -0.51
     Titus
    -0.51
    jComboBox
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.65
    cshtml
    0.63
    TypedDataSet
    0.58
     aidant
    0.56
     tadi
    0.54
     оригіналу
    0.54
    transQ
    0.53
     JADX
    0.53
    lück
    0.52
    sizeCache
    0.52
    Activations Density 0.292%

    No Known Activations