© 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. 11595
    Prev
    Next
    INDEX
    Explanations

    a combination of modal verbs, subjective pronouns, and words implying app ownership in the context of software or technology.

    oai_token-act-pair · gemini-2.0-flash

    Possibilities and suggestions

    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
     autorytatywna
    -0.80
     AssemblyCulture
    -0.73
     pinulongan
    -0.73
    WithIOException
    -0.73
     <=",
    -0.68
    IsMutable
    -0.66
     douceur
    -0.66
    ArrowToggle
    -0.65
    
    -0.64
    UnknownFields
    -0.63
    POSITIVE LOGITS
     your
    0.68
    {"
    0.61
    your
    0.59
     YOUR
    0.57
     Your
    0.56
    あなたの
    0.56
    YOUR
    0.56
    tisol
    0.56
     ChromeDriver
    0.54
    vete
    0.52
    Activations Density 1.514%

    No Known Activations