© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12981
    Prev
    Next
    INDEX
    Explanations

    the word 'prepared' and sometimes also finds the word 'ruled'

    oai_token-act-pair · gemini-2.0-flash

    prepared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -1.33
     prepared
    -0.98
    prepared
    -0.75
     Prepared
    -0.67
    Prepared
    -0.59
     harm
    -0.57
    PARED
    -0.50
    ↵↵
    -0.49
     autorytatywna
    -0.45
    //
    -0.44
    POSITIVE LOGITS
    UserScript
    0.82
     BrowserModule
    0.65
     cherchés
    0.65
     MainAxisSize
    0.62
    straints
    0.61
     citoy
    0.60
     Mérimée
    0.60
     }{@
    0.59
     BorderSide
    0.59
     ویکی‌پدیای
    0.59
    Activations Density 1.432%

    No Known Activations