© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13703
    Prev
    Next
    INDEX
    Explanations

    the number 4 in various contexts

    oai_token-act-pair · gemini-2.0-flash

    mentions of "four" or variations thereof

    np_token-act-pair-logits · gpt-4o-mini

    four

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     referenties
    -0.84
    addCriterion
    -0.84
    Personendaten
    -0.82
    ViewImports
    -0.82
    évaluateur
    -0.81
    WebVitals
    -0.79
    TypedDataSet
    -0.77
     MenuView
    -0.76
     resourceCulture
    -0.76
    ViewFeatures
    -0.76
    POSITIVE LOGITS
     para
    0.54
    chan
    0.53
    tell
    0.49
    th
    0.48
    alan
    0.47
    cha
    0.46
     four
    0.45
    mark
    0.45
    od
    0.44
    para
    0.44
    Activations Density 1.172%

    No Known Activations