© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4124
    Prev
    Next
    INDEX
    Explanations

    the words 'get' and 'set' in what appears to be code

    oai_token-act-pair · gemini-2.0-flash

    get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Type
    -0.82
    Image
    -0.82
    Price
    -0.81
    Total
    -0.80
    Date
    -0.80
    Cpf
    -0.77
    Email
    -0.75
    Max
    -0.75
    Current
    -0.75
    Color
    -0.75
    POSITIVE LOGITS
     invokingState
    0.50
     autorytatywna
    0.48
     edn
    0.47
    modelBuilder
    0.47
     betweenstory
    0.46
    laise
    0.45
     становника
    0.45
     lopp
    0.45
    solid
    0.44
    ✭✭
    0.44
    Activations Density 0.889%

    No Known Activations