© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4902
    Prev
    Next
    INDEX
    Explanations

    the word "head" and its related usages

    oai_token-act-pair · gemini-2.0-flash

    words and terms related to 'head'

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

    head

    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
     escala
    -0.62
    jaardag
    -0.55
     skala
    -0.51
     aveug
    -0.50
     découver
    -0.49
     généraux
    -0.48
     Baillargeon
    -0.47
     عج
    -0.47
     Gump
    -0.47
     AssemblyCompany
    -0.46
    POSITIVE LOGITS
    TagMode
    0.69
    EDEFAULT
    0.63
    routeProvider
    0.56
     مرئيه
    0.55
    EndGlobalSection
    0.54
    rungsseite
    0.53
    AntiForgeryToken
    0.53
    WireFormat
    0.53
    EndProject
    0.53
    enumi
    0.50
    Activations Density 0.559%

    No Known Activations