© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9711
    Prev
    Next
    INDEX
    Explanations

    the article "a" and words that often follow it, such as "lot", "large", "number," or a person's name.

    oai_token-act-pair · gemini-2.0-flash

    multiple quantities or abundance

    np_token-act-pair-logits · gpt-4o-mini

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ArrowToggle
    -0.66
    sstelle
    -0.56
    erb
    -0.55
    ajuku
    -0.55
    はじめに
    -0.54
    swire
    -0.54
     neither
    -0.52
    isela
    -0.52
    fjspx
    -0.52
    şme
    -0.51
    POSITIVE LOGITS
     montón
    0.93
     lot
    0.92
     plurality
    0.82
     amount
    0.81
     multitude
    0.80
    amount
    0.78
     plethora
    0.78
     LOT
    0.76
     majority
    0.70
     aantal
    0.70
    Activations Density 1.694%

    No Known Activations