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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7442
    Prev
    Next
    INDEX
    Explanations

    the word "opportunities" and closely related descriptions of employment or options

    oai_token-act-pair · gemini-2.0-flash

    opportunities

    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
     -
    -0.86
     (
    -0.86
    ,
    -0.75
    :
    -0.73
     to
    -0.72
     
    -0.71
    ↵
    -0.68
     I
    -0.67
    -
    -0.66
     of
    -0.66
    POSITIVE LOGITS
     myſelf
    1.45
    ſelf
    1.41
     Jefus
    1.40
     $_"
    1.38
     themſelves
    1.38
     doubtnut
    1.36
     Theſe
    1.36
    ^(@)
    1.35
     itſelf
    1.34
    .",
    
    1.34
    Activations Density 0.511%

    No Known Activations