© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5580
    Prev
    Next
    INDEX
    Explanations

    code documentation

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     vitamins
    -0.81
     Vit
    -0.79
     vitaminas
    -0.68
     Vitamins
    -0.67
     витами
    -0.66
    Вита
    -0.65
    Vit
    -0.64
     VIT
    -0.62
     vitamine
    -0.62
     vit
    -0.61
    POSITIVE LOGITS
    <bos>
    0.74
      (
    0.57
    endpush
    0.57
    readystatechange
    0.55
    PullParser
    0.54
    openConnection
    0.53
    Havolalar
    0.52
    
    0.52
     BoxDecoration
    0.52
    emlrt
    0.52
    Activations Density 0.466%

    No Known Activations