© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9781
    Prev
    Next
    INDEX
    Explanations

    the number one and related terms in mathematical contexts

    oai_token-act-pair · gemini-2.0-flash

    one/unity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    rboles
    -0.48
     AssemblyProduct
    -0.47
    <bos>
    -0.45
     RequestMethod
    -0.44
    wochen
    -0.43
    IsPostBack
    -0.43
    Edited
    -0.42
    dulo
    -0.41
    Höhe
    -0.41
     Exit
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.90
     NSCoder
    0.81
     تضيفلها
    0.73
     دیکھیے
    0.70
     snippetHide
    0.70
    солю
    0.69
    Datuak
    0.68
     विश्वसनीयता
    0.68
     NUKAT
    0.65
    GeneratedCode
    0.65
    Activations Density 2.813%

    No Known Activations