© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5644
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in storytelling to establish tense and describe events, often including prepositions and time references.

    oai_token-act-pair · gemini-2.0-flash

    estimation/probability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Italijanski
    -0.76
    "}")
    -0.74
    kháu
    -0.71
    انيف
    -0.71
    :✨
    -0.71
     ModelExpression
    -0.68
    #
    -0.68
    Демографія
    -0.67
     Савезне
    -0.62
    webElementXpaths
    -0.61
    POSITIVE LOGITS
     probably
    0.96
     maybe
    0.83
     perhaps
    0.82
     atleast
    0.80
    probably
    0.79
    至少
    0.79
     almeno
    0.77
     approximately
    0.76
    maybe
    0.76
     about
    0.74
    Activations Density 5.890%

    No Known Activations