© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8576
    Prev
    Next
    INDEX
    Explanations

    words related to modularity in programming code

    oai_token-act-pair · gemini-2.0-flash

    computer interfaces

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     interface
    -2.19
     Interface
    -2.14
     interfaces
    -2.11
    interface
    -1.99
    Interface
    -1.94
     Interfaces
    -1.91
     INTERFACE
    -1.87
    INTERFACE
    -1.64
    interfaces
    -1.62
    Interfaces
    -1.61
    POSITIVE LOGITS
    yorsunuz
    0.57
    izoen
    0.55
     sessionFactory
    0.50
    kuuta
    0.48
    yoruz
    0.47
    proud
    0.46
    STUD
    0.46
    المشاركات
    0.45
     mờ
    0.45
     Spisak
    0.44
    Activations Density 1.807%

    No Known Activations