© 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. 2421
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gemini-2.0-flash

    scientific and technical writing

    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
    WithIOException
    -0.96
     nineteen
    -0.91
     seventies
    -0.89
    GEBURTSDATUM
    -0.88
    AccessorTable
    -0.84
     seventeenth
    -0.84
    RegistryLite
    -0.82
     snippetHide
    -0.80
    tagHelperRunner
    -0.79
     Nineteen
    -0.77
    POSITIVE LOGITS
     favorables
    0.49
     présidenti
    0.46
    gow
    0.44
     civiles
    0.44
     Cody
    0.44
     Butler
    0.43
    IBIL
    0.42
     judicia
    0.42
    soundcloud
    0.42
    τρα
    0.41
    Activations Density 0.556%

    No Known Activations