© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15521
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear in an internet chat room

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     متعلقه
    -0.79
    Cordialement
    -0.71
     Sein
    -0.69
    alors
    -0.69
     disponibilités
    -0.68
     مشين
    -0.67
    новниш
    -0.66
    omock
    -0.65
    GraphicsUnit
    -0.65
     בתח
    -0.65
    POSITIVE LOGITS
    <bos>
    0.81
     conveys
    0.56
     familiare
    0.55
     marito
    0.54
     servici
    0.54
     giuri
    0.52
     sprá
    0.51
     conveyed
    0.51
     ää
    0.50
     attentive
    0.48
    Activations Density 0.236%

    No Known Activations