© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2828
    Prev
    Next
    INDEX
    Explanations

    multiple different miscellaneous features including proper nouns, names of months, non-English words and phrases, and formatting characters

    oai_token-act-pair · gemini-2.0-flash

    technical code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -
    -0.54
    issage
    -0.49
    Źródło
    -0.48
    Díky
    -0.48
     chaves
    -0.47
    tamount
    -0.47
     SLP
    -0.45
    dds
    -0.44
     estação
    -0.44
    éal
    -0.44
    POSITIVE LOGITS
     estekak
    0.67
    MemoryWarning
    0.66
    queryInterface
    0.59
    MigrationBuilder
    0.57
    ViewFeatures
    0.57
    SequentialGroup
    0.57
     <<<<<<<<<<<<<<
    0.56
     AspNetCore
    0.56
    onOptions
    0.56
    WarningLevel
    0.56
    Activations Density 0.564%

    No Known Activations