© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7918
    Prev
    Next
    INDEX
    Explanations

    the word "background"

    oai_token-act-pair · gemini-2.0-flash

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.57
     in
    -1.24
      
    -1.17
    -
    -1.16
    ,
    -1.16
     and
    -1.16
    .
    -1.15
     the
    -1.15
    y
    -1.14
     (
    -1.13
    POSITIVE LOGITS
     Efq
    2.88
     myſelf
    2.45
    ^(@)
    2.41
     Jefus
    2.38
     itſelf
    2.31
     Monfieur
    2.31
     Majefty
    2.30
     purpoſe
    2.23
     ―――――
    2.19
     ſtate
    2.17
    Activations Density 1.115%

    No Known Activations