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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8454
    Prev
    Next
    INDEX
    Explanations

    the word "cold"

    oai_token-act-pair · gemini-2.0-flash

    cold

    np_max-act · gemini-2.0-flash

    ▁cold

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    -0.59
    zA
    -0.57
     par
    -0.54
    ]][
    -0.54
     infine
    -0.51
     lenker
    -0.50
    extendable
    -0.50
    Amid
    -0.49
    ,'\
    -0.49
    _),
    -0.49
    POSITIVE LOGITS
    berdayakan
    0.87
    DockStyle
    0.81
     ThemeData
    0.78
    setVerticalGroup
    0.75
    makeConstraints
    0.69
     debout
    0.68
    CppCodeGen
    0.66
     juridiques
    0.66
    awakeFromNib
    0.65
     MaterialApp
    0.65
    Activations Density 1.824%
    No Known Activations