© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 48
    Prev
    Next
    INDEX
    Explanations

    questions involving the words 'why' and 'how'

    oai_token-act-pair · gemini-2.0-flash

    why

    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
     as
    -0.47
    ♥♥
    -0.47
     Why
    -0.42
    torie
    -0.42
     m
    -0.42
     насеље
    -0.42
     Paglinawan
    -0.40
     mit
    -0.39
     Do
    -0.39
     ta
    -0.38
    POSITIVE LOGITS
     تانيه
    0.99
     betweenstory
    0.95
    ReusableCell
    0.91
    TagMode
    0.90
     ویکی‌پدیای
    0.86
    出版年
    0.84
    ftagPool
    0.83
    脚注の使い方
    0.80
    InstanceState
    0.79
     doesn
    0.77
    Activations Density 4.950%

    No Known Activations