© 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. 10248
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in online chat, especially in French

    oai_token-act-pair · gemini-2.0-flash

    pas

    np_max-act · gemini-2.0-flash

    pas

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    findpost
    -0.79
    atteindre
    -0.68
     Reisedaten
    -0.67
    esca
    -0.66
     newList
    -0.66
    İstinadlar
    -0.65
    terness
    -0.65
    XmlAccessType
    -0.64
     newName
    -0.63
    ZIONI
    -0.63
    POSITIVE LOGITS
    <bos>
    0.94
    ↵↵
    0.60
    The
    0.57
    I
    0.56
     nails
    0.50
    et
    0.50
     gingerbread
    0.49
     aload
    0.47
     aclar
    0.47
    '
    0.47
    Activations Density 0.324%

    No Known Activations