© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13055
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as language keywords, variables, and operators

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     kasarigan
    -0.88
    AddTagHelper
    -0.86
    twimg
    -0.84
    ècie
    -0.73
    Зноскі
    -0.71
    XmlAccessType
    -0.68
    AsUp
    -0.68
    RepeatedField
    -0.68
     nakalista
    -0.67
    Tembelea
    -0.65
    POSITIVE LOGITS
    +:+
    0.43
    @
    0.41
    mesi
    0.40
    mi
    0.39
     Pokies
    0.39
     EnglishChoose
    0.36
    ford
    0.36
    source
    0.36
    such
    0.36
    ferd
    0.36
    Activations Density 4.361%

    No Known Activations