© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11503
    Prev
    Next
    INDEX
    Explanations

    the word 'secret' and related words

    oai_token-act-pair · gemini-2.0-flash

    secret

    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
    VersionUID
    -0.75
    存于互联网档案馆
    -0.74
     surla
    -0.71
     مرئيه
    -0.69
    er
    -0.65
     onAnimation
    -0.64
    WaitGroup
    -0.61
    ReusableCell
    -0.60
    InputBorder
    -0.60
     См
    -0.60
    POSITIVE LOGITS
     Meksiku
    0.68
     Poisson
    0.63
     Harz
    0.58
    ecto
    0.57
     Breslau
    0.57
     ouvido
    0.56
    ↵
    0.56
     lyst
    0.56
     pensamentos
    0.56
     dạng
    0.54
    Activations Density 0.909%

    No Known Activations