© 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. 14547
    Prev
    Next
    INDEX
    Explanations

    text containing mathematical formulas and symbols

    oai_token-act-pair · gemini-2.0-flash

    Code/math

    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
    <bos>
    -0.66
    sellors
    -0.47
     ISTAT
    -0.47
    u
    -0.47
    OrNil
    -0.45
    könyv
    -0.44
    كز
    -0.43
     stessi
    -0.42
     nélk
    -0.42
    BASEPATH
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.69
    complexType
    0.63
    yarnpkg
    0.60
    #![
    0.59
    исленность
    0.58
    gameserver
    0.56
    ddha
    0.56
    يكب
    0.54
    RectangleBorder
    0.53
    AccessFile
    0.52
    Activations Density 52.711%

    No Known Activations