© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3158
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific and technical descriptions, especially of how things depend on each other.

    oai_token-act-pair · gemini-2.0-flash

    dependencies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     dependency
    -2.59
     dependence
    -2.52
     depend
    -2.42
     dependent
    -2.41
     depended
    -2.36
     Dependence
    -2.31
     Dependent
    -2.28
     Dependency
    -2.19
     dependant
    -2.16
     dependencies
    -2.13
    POSITIVE LOGITS
    \{\\
    0.68
     Catawiki
    0.53
     estekak
    0.52
    WarningLevel
    0.51
     totally
    0.50
     wholly
    0.49
     Wikimedijinoj
    0.49
    signable
    0.48
    elemField
    0.48
    WithIOException
    0.47
    Activations Density 3.996%

    No Known Activations