© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7673
    Prev
    Next
    INDEX
    Explanations

    the word "there" as well as other words and phrases colocated with "there"

    oai_token-act-pair · gemini-2.0-flash

    Introduces topic

    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
    ↵
    -0.68
      
    -0.66
     
    -0.62
     the
    -0.60
     has
    -0.59
    .
    -0.59
     (
    -0.58
     is
    -0.55
     was
    -0.55
    -
    -0.54
    POSITIVE LOGITS
     Anſ
    1.03
     ―――――
    0.98
    >*/
    0.97
     Theſe
    0.97
     houſe
    0.96
     Houſe
    0.94
     ་་
    0.93
     myſelf
    0.93
    ngdoc
    0.92
     Majefty
    0.91
    Activations Density 0.844%

    No Known Activations