© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12738
    Prev
    Next
    INDEX
    Explanations

    C++ code syntax, specifically namespaces, colons and templates

    oai_token-act-pair · gemini-2.0-flash

    ::

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ::
    -1.26
     ::
    -0.85
    ChildScrollView
    -0.75
    >::
    -0.74
    ::_
    -0.73
    ::$
    -0.69
    ::__
    -0.66
    :::
    -0.66
     :::
    -0.60
    ::::
    -0.54
    POSITIVE LOGITS
     disambiguazione
    0.87
    Personendaten
    0.70
    oredCriteria
    0.66
    IUrlHelper
    0.65
    expandindo
    0.59
     članak
    0.58
     invokingState
    0.57
     мәкал
    0.57
     snippetHide
    0.57
    RTLD
    0.57
    Activations Density 0.390%

    No Known Activations