© 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. 8903
    Prev
    Next
    INDEX
    Explanations

    strong language and swearing

    oai_token-act-pair · gemini-2.0-flash

    strong exclamations or offensive language

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

    swear words

    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
     ویکی‌آمباردا
    -0.56
    atação
    -0.56
    ffekt
    -0.56
    ราะ
    -0.55
    énario
    -0.55
    hamos
    -0.51
     виправивши
    -0.51
     Référence
    -0.50
    gorithm
    -0.50
    észet
    -0.50
    POSITIVE LOGITS
    parsedMessage
    0.75
    transQ
    0.66
    RegressionTest
    0.59
    exitRule
    0.58
     betweenstory
    0.55
    webElementXpaths
    0.52
    GeneratedCode
    0.49
    NameInMap
    0.47
    risse
    0.44
    XmlAccessType
    0.43
    Activations Density 3.948%

    No Known Activations