© 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. 4877
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning ones abilities or the quality of something

    oai_token-act-pair · gemini-2.0-flash

    hesitation and uncertainty

    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
    Viitteet
    -0.61
    onsense
    -0.54
    yesterday
    -0.54
     belongs
    -0.53
     indifer
    -0.53
    ื้อ
    -0.52
    ugal
    -0.52
     VizieR
    -0.52
    ignement
    -0.51
    licated
    -0.51
    POSITIVE LOGITS
     typically
    0.79
    httphttps
    0.69
    最快更新
    0.67
    XmlIgnore
    0.63
     ویکی‌پدیا
    0.63
    IntoConstraints
    0.62
    modelBuilder
    0.60
    databind
    0.60
    AccessorTable
    0.59
     Typically
    0.59
    Activations Density 2.543%

    No Known Activations