© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4136
    Prev
    Next
    INDEX
    Explanations

    sentences ending in punctuation

    oai_token-act-pair · gemini-2.0-flash

    advice and instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     consume
    -0.77
     take
    -0.71
     make
    -0.70
     decide
    -0.70
     verify
    -0.68
     go
    -0.68
     do
    -0.68
     calculate
    -0.68
     ensure
    -0.66
     modify
    -0.66
    POSITIVE LOGITS
    ValueStyle
    1.05
    Šaltiniai
    0.79
    Демографія
    0.75
    SharedDtor
    0.69
     Train
    0.67
     חיצוניים
    0.67
    NewUrlParser
    0.63
     Cover
    0.61
    IntoConstraints
    0.61
    Skocz
    0.60
    Activations Density 2.482%

    No Known Activations