© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8682
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or discourse markers, often near words implying emotion

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ,
    -2.08
    .
    -1.20
    :
    -1.15
    ;
    -1.13
    ,,
    -1.02
    ,.
    -0.98
    ,...
    -0.94
    )
    -0.93
    ,<
    -0.92
    ',
    -0.92
    POSITIVE LOGITS
     whoſe
    0.71
    HostException
    0.70
     EconPapers
    0.69
     Theſe
    0.68
    Vanjske
    0.68
     becauſe
    0.66
    canestro
    0.64
     stanovnika
    0.63
     Shakspeare
    0.61
     myſelf
    0.61
    Activations Density 9.538%

    No Known Activations