© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 843
    Prev
    Next
    INDEX
    Explanations

    words associated with scientific analysis, especially of ancient life and also crime

    oai_token-act-pair · gemini-2.0-flash

    variations of "find"

    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
     &___
    -0.69
    EndInit
    -0.69
    SharedDtor
    -0.67
    __':
    -0.66
    NameInMap
    -0.65
    Diwedd
    -0.64
    Rhestr
    -0.62
     ویکی‌پدیای
    -0.61
    LEncoder
    -0.61
    istoitu
    -0.59
    POSITIVE LOGITS
     found
    2.13
     discovery
    1.93
     discovered
    1.93
    found
    1.88
     Found
    1.84
     find
    1.84
     finds
    1.84
     finding
    1.81
    find
    1.77
    Found
    1.72
    Activations Density 2.566%

    No Known Activations