© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11987
    Prev
    Next
    INDEX
    Explanations

    the word "settled."

    oai_token-act-pair · gemini-2.0-flash

    settled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     autorytatywna
    -0.84
     itſelf
    -0.80
    )')
    -0.77
    Vidite
    -0.74
     internetowa
    -0.73
    WebKit
    -0.71
    EndGlobalSection
    -0.71
    )');
    -0.70
    abuena
    -0.69
     myſelf
    -0.69
    POSITIVE LOGITS
     "..\..\
    0.62
     favorite
    0.56
     ///
    0.56
     sred
    0.53
    дем
    0.52
     Apes
    0.51
    طفال
    0.49
    ▾
    0.49
     celo
    0.48
    ಾರ
    0.48
    Activations Density 0.545%

    No Known Activations