© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10968
    Prev
    Next
    INDEX
    Explanations

    latex and other symbols that appear in scientific documents and code

    oai_token-act-pair · gemini-2.0-flash

    code, math, statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    lité
    -0.54
    of
    -0.52
    isations
    -0.51
    AnchorStyles
    -0.51
    XtraGrid
    -0.50
    our
    -0.50
    дём
    -0.50
    istry
    -0.49
    mmers
    -0.49
    "];
    -0.48
    POSITIVE LOGITS
    verwijspagina
    0.62
    rungsseite
    0.60
    AsUp
    0.55
     Cedex
    0.54
    NameInMap
    0.53
    tagHelperRunner
    0.53
    skosten
    0.50
     Constitucional
    0.49
    pisah
    0.49
     aveug
    0.49
    Activations Density 14.135%

    No Known Activations