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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6175
    Prev
    Next
    INDEX
    Explanations

    contextual words like bit, of, and that

    oai_token-act-pair · gemini-2.0-flash

    terms related to theories or theoretical concepts

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

    theory

    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
     resourceCulture
    -0.81
    AndEndTag
    -0.61
     initComponents
    -0.60
    expandindo
    -0.57
    DockStyle
    -0.57
    ENCODING
    -0.56
    乓
    -0.54
    RenderAtEndOf
    -0.54
    SourceChecksum
    -0.52
    ashvili
    -0.50
    POSITIVE LOGITS
     theory
    1.64
     Theory
    1.35
    theory
    1.33
    Theory
    1.28
     theoretical
    1.28
     theories
    1.27
     THEORY
    1.26
     teori
    1.22
    THEORY
    1.21
     théorie
    1.20
    Activations Density 2.937%

    No Known Activations