© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1233
    Prev
    Next
    INDEX
    Explanations

    mentions of machine learning

    oai_token-act-pair · gemini-2.0-flash

    machine learning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     learn
    -2.89
     learning
    -2.86
    learn
    -2.69
     Learn
    -2.69
    Learn
    -2.67
     learns
    -2.66
     learned
    -2.64
     Learning
    -2.63
     LEARN
    -2.59
    Learning
    -2.56
    POSITIVE LOGITS
    terase
    0.53
     hashCode
    0.52
    XmlAccessType
    0.51
    setVerticalGroup
    0.51
    HashCode
    0.48
    ugno
    0.46
    setAdapter
    0.46
    LayoutConstraint
    0.46
    GetHashCode
    0.46
    Cubit
    0.46
    Activations Density 2.373%

    No Known Activations