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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4641
    Prev
    Next
    INDEX
    Explanations

    instances of the words "will", "can", "could", "you", or "I" in close proximity

    oai_token-act-pair · gemini-2.0-flash

    Addressing the reader

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    toc
    -0.45
    
    -0.43
    bung
    -0.42
     tinh
    -0.41
     kans
    -0.39
     cass
    -0.38
     MTN
    -0.38
    Plan
    -0.38
     geven
    -0.38
    Tag
    -0.38
    POSITIVE LOGITS
     समीक्षक
    0.82
     NDEBUG
    0.73
     Paglinawan
    0.72
    مصادر
    0.71
     مشين
    0.71
     ―――――
    0.71
     myſelf
    0.70
    onStop
    0.69
    kuuta
    0.68
    abestanden
    0.67
    Activations Density 1.744%

    No Known Activations