© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10496
    Prev
    Next
    INDEX
    Explanations

    phrases implying a state of being and the word "remained"

    oai_token-act-pair · gemini-2.0-flash

    words related to silence or quietness

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

    silence or quiet

    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
    withCredentials
    -0.46
     riuscito
    -0.44
    ClientSize
    -0.43
     discut
    -0.39
    nissen
    -0.39
    ⏟
    -0.39
    <tbody>
    -0.39
     teme
    -0.38
    WindowListener
    -0.38
    aspetto
    -0.38
    POSITIVE LOGITS
     silent
    1.20
     quiet
    1.05
    BeginContext
    0.99
     silence
    0.99
    silent
    0.97
     mute
    0.91
    silence
    0.85
    quiet
    0.84
     Silent
    0.84
     silencio
    0.80
    Activations Density 1.403%

    No Known Activations