© 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. 3253
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets and related terminology, but also some Spanish words

    oai_token-act-pair · gemini-2.0-flash

    Multiple languages

    np_max-act-logits · gemini-2.0-flash

    Spanish

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     '\\;'
    -0.89
     estimés
    -0.89
     للمعارف
    -0.81
     transfieras
    -0.71
    ValueStyle
    -0.71
    Tembelea
    -0.71
    expandindo
    -0.68
    bootstrapcdn
    -0.68
     تضيفلها
    -0.67
     noDo
    -0.66
    POSITIVE LOGITS
    IBOutlet
    0.48
     Bes
    0.45
     via
    0.42
    iseur
    0.41
    pheres
    0.40
    enumi
    0.40
    konos
    0.40
    kar
    0.39
     bes
    0.39
     kar
    0.39
    Activations Density 0.282%

    No Known Activations