© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11177
    Prev
    Next
    INDEX
    Explanations

    code-related words with the words 'ratio', 'flag', and 'override'

    oai_token-act-pair · gemini-2.0-flash

    Code or configurations

    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
    !
    -0.65
      
    -0.63
    _
    -0.59
     
    -0.57
    <strong>
    -0.56
    (
    -0.56
    .
    -0.55
     (
    -0.54
    :
    -0.54
    ↵
    -0.54
    POSITIVE LOGITS
    ^(@)
    1.21
     Efq
    0.98
     jsPsych
    0.97
     photolibrary
    0.97
    ^(@
    0.95
     (\<
    0.92
     doubtnut
    0.89
     tslint
    0.87
    ."</
    0.85
    fhir
    0.84
    Activations Density 1.746%

    No Known Activations