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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 9953
    Prev
    Next
    INDEX
    Explanations

    mentions of presidents, particularly Donald Trump and Barack Obama

    oai_token-act-pair · gemini-2.0-flash

    President

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    contentLoaded
    -0.96
    /**
    -0.95
    HasAnnotation
    -0.89
    ſelf
    -0.87
    "],
    
    -0.85
     Efq
    -0.83
     ſtate
    -0.83
     Cæsar
    -0.81
    ьаж
    -0.79
     BoxFit
    -0.79
    POSITIVE LOGITS
     sur
    0.41
    PLAUSE
    0.39
    less
    0.36
     APPEND
    0.36
     viewDidLoad
    0.35
     le
    0.35
    #
    0.35
     super
    0.35
     professionnel
    0.34
    Debian
    0.34
    Activations Density 0.793%

    No Known Activations