© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 14111
    Prev
    Next
    INDEX
    Explanations

    words related to the layout or design of something, whether physical or organizational

    oai_token-act-pair · gemini-2.0-flash

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     structure
    -2.52
    structure
    -2.34
     Structure
    -2.33
    Structure
    -2.25
     structures
    -2.13
     STRUCTURE
    -2.00
     Structures
    -1.99
     Struktur
    -1.91
    structures
    -1.87
     estructura
    -1.84
    POSITIVE LOGITS
    kens
    0.52
    rayage
    0.45
     Blend
    0.44
     Compilation
    0.44
     Paraly
    0.43
    Xa
    0.43
     Aggreg
    0.43
    phazard
    0.42
     TRANSLATION
    0.41
    Compilation
    0.41
    Activations Density 3.926%

    No Known Activations