© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9194
    Prev
    Next
    INDEX
    Explanations

    C++ code syntax, especially related to templates, namespaces, and class definitions.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ########.
    -0.80
    balleur
    -0.75
    ReusableCell
    -0.71
    +:+
    -0.69
    TestingModule
    -0.63
    :+:
    -0.62
     okuyayım
    -0.62
    SpringRunner
    -0.60
     IOError
    -0.60
    #+#
    -0.59
    POSITIVE LOGITS
    endrait
    0.54
     isolato
    0.50
     uſed
    0.50
     tested
    0.46
     eſ
    0.46
     becauſe
    0.46
     raiſ
    0.46
     Архів
    0.46
     ferait
    0.45
    ſelf
    0.45
    Activations Density 3.106%

    No Known Activations