© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7906
    Prev
    Next
    INDEX
    Explanations

    code snippets and json-like structures, especially those containing the word "foo"

    oai_token-act-pair · gemini-2.0-flash

    Code-related syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     <=",
    -0.60
     Stabilization
    -0.59
     Tect
    -0.58
    ToScroll
    -0.58
     tect
    -0.57
     Trials
    -0.57
     saites
    -0.57
    othelial
    -0.56
     Langmuir
    -0.56
     dilatation
    -0.56
    POSITIVE LOGITS
    __'
    0.52
    {}",
    0.50
    $")
    0.49
     %@",
    0.48
    %@",
    0.48
    ?')
    0.47
    ?");
    0.47
     "];
    0.46
    ’”
    0.46
    __':
    
    0.45
    Activations Density 21.964%

    No Known Activations