© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6515
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or equations

    oai_token-act-pair · gemini-2.0-flash

    programming or mathematical symbols

    np_token-act-pair-logits · gpt-4o-mini

    mathematical notation and 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DoubleQuotes
    -0.66
    ]--;
    -0.64
    InteropServices
    -0.55
    endpush
    -0.50
    ocarditis
    -0.49
    достатки
    -0.49
    --}}
    -0.48
    訳
    -0.47
    isOk
    -0.47
    URIComponent
    -0.47
    POSITIVE LOGITS
    +#+#
    0.68
    ReusableCell
    0.62
     estekak
    0.56
    \{\\
    0.56
    setopt
    0.54
    ########.
    0.53
    ंदीखरीदारी
    0.52
    geschäft
    0.52
    CloseOperation
    0.51
    awaiter
    0.50
    Activations Density 6.096%

    No Known Activations