© 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. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11888
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns like band names, institutions, legal terminology, and food items

    oai_token-act-pair · gemini-2.0-flash

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    AddTagHelper
    -0.95
    aarrggbb
    -0.94
     CreateTagHelper
    -0.84
    Tembelea
    -0.83
    ########.
    -0.83
     للمعارف
    -0.82
    saraba
    -0.82
     cherchés
    -0.80
    WithIOException
    -0.78
    ItemBackground
    -0.77
    POSITIVE LOGITS
    .
    0.43
     charges
    0.42
     mid
    0.42
    ↵↵
    0.42
    ‎
    0.41
     đảo
    0.40
    Works
    0.40
    半
    0.39
    Band
    0.39
     CommandType
    0.39
    Activations Density 0.378%

    No Known Activations