© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11269
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets including operators, and certain keywords like "decimal", and "mozilla.org"

    oai_token-act-pair · gemini-2.0-flash

    programming code or operators

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

    code-related snippets

    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
     *
    -0.48
    ático
    -0.45
    TRANSFORM
    -0.44
     thereto
    -0.43
    ENSUS
    -0.42
     ring
    -0.41
     parfait
    -0.41
    square
    -0.40
    OPH
    -0.40
     trans
    -0.40
    POSITIVE LOGITS
    +#+#
    1.00
    windowFixed
    0.99
    Personendaten
    0.94
    ########.
    0.93
     lenker
    0.90
    GEBURTSDATUM
    0.89
     estekak
    0.89
    SBATCH
    0.86
    oredCriteria
    0.85
    évaluateur
    0.84
    Activations Density 3.526%

    No Known Activations