© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7834
    Prev
    Next
    INDEX
    Explanations

    references to coffee, tea, and growing seasons

    oai_token-act-pair · gemini-2.0-flash

    coffee

    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
     Efq
    -1.84
     Monfieur
    -1.48
     ―――――
    -1.48
    ſelves
    -1.48
     Houſe
    -1.47
     Majefty
    -1.46
     myſelf
    -1.42
     photolibrary
    -1.42
    ſelf
    -1.40
     ་་
    -1.38
    POSITIVE LOGITS
     the
    0.89
     (
    0.78
     a
    0.73
     some
    0.72
     it
    0.69
     I
    0.69
     as
    0.68
     
    0.67
     eventually
    0.67
     M
    0.66
    Activations Density 1.703%

    No Known Activations