© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13238
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to rules and processes

    oai_token-act-pair · gemini-2.0-flash

    legal, finance, education context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     "
    -0.46
     in
    -0.44
     off
    -0.42
     and
    -0.40
    +
    -0.40
    ,
    -0.40
     i
    -0.40
    <eos>
    -0.38
     “
    -0.38
    [
    -0.38
    POSITIVE LOGITS
     ―――――
    0.96
     ſtate
    0.95
     мәкал
    0.94
     myſelf
    0.90
     neceff
    0.90
    tvguidetime
    0.90
     jScrollPane
    0.90
    }}]{
    0.90
     juſ
    0.89
    Autoritní
    0.89
    Activations Density 4.439%

    No Known Activations