© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10981
    Prev
    Next
    INDEX
    Explanations

    the word "one" or "an"

    oai_token-act-pair · gemini-2.0-flash

    One

    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
    المناصب
    -0.75
    .",
    -0.75
    '),
    -0.68
    رشف
    -0.66
    ++];
    -0.66
     سكانية
    -0.66
    \{\\
    -0.64
     kaarangay
    -0.63
    '));
    -0.63
     שוליים
    -0.63
    POSITIVE LOGITS
    ΤΗ
    0.55
    իս
    0.54
     rosse
    0.51
    tag
    0.50
     bassi
    0.50
    va
    0.49
     attendu
    0.49
     carré
    0.49
    yal
    0.48
    DateFormat
    0.48
    Activations Density 4.608%

    No Known Activations