© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12141
    Prev
    Next
    INDEX
    Explanations

    the word "every" and other words that often precede it

    oai_token-act-pair · gemini-2.0-flash

    every

    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
    setDefault
    -0.45
    чта
    -0.39
    [::-
    -0.39
     demikian
    -0.38
    aults
    -0.38
    obal
    -0.38
     Herzens
    -0.37
    Continue
    -0.37
     Großen
    -0.37
    unica
    -0.37
    POSITIVE LOGITS
    UserScript
    0.79
    存于互联网档案馆
    0.78
     يتيمه
    0.77
    liothèque
    0.76
    fjspx
    0.73
    KommentareTeilen
    0.73
    
    0.72
    StoryboardSegue
    0.70
    fromnode
    0.70
    InputBorder
    0.70
    Activations Density 1.302%

    No Known Activations