Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7186
    Prev
    Next
    INDEX
    Explanations

    the string "temp" within code, especially alongside byte arrays and conditional statements.

    oai_token-act-pair · gemini-2.0-flash

    temp

    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
     the
    -1.37
     
    -1.34
    ,
    -1.27
      
    -1.20
     a
    -1.18
    ↵↵
    -1.14
    .
    -1.12
    ↵
    -1.09
     it
    -1.05
     an
    -1.04
    POSITIVE LOGITS
     Efq
    2.80
     myſelf
    2.56
    ſelf
    2.38
     Jefus
    2.34
     Monfieur
    2.33
     themſelves
    2.31
     itſelf
    2.31
     Theſe
    2.27
     Majefty
    2.27
    ſelves
    2.27
    Activations Density 3.070%

    No Known Activations