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. 7156
    Prev
    Next
    INDEX
    Explanations

    the C preprocessor directive '#else'

    oai_token-act-pair · gemini-2.0-flash

    else

    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
     Monfieur
    -0.93
     greateſt
    -0.90
     Theſe
    -0.88
     ſmall
    -0.88
     purpoſe
    -0.87
     houſe
    -0.86
     pleaſure
    -0.81
     ſtate
    -0.80
    вгений
    -0.80
    ſelf
    -0.80
    POSITIVE LOGITS
    __":
    0.69
    __":
    
    0.68
    __':
    0.66
    __':
    
    0.65
     ("
    0.60
    We
    0.59
     pedimos
    0.59
     (“
    0.56
    '
    0.55
     («
    0.53
    Activations Density 2.404%

    No Known Activations