© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15059
    Prev
    Next
    INDEX
    Explanations

    C++ code, especially template metaprogramming and clang-related code

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    hyrchwyd
    -0.63
     متعلقه
    -0.61
     MediatR
    -0.56
     arbitrators
    -0.52
     iprot
    -0.52
     uve
    -0.51
     columb
    -0.50
     OMITBAD
    -0.50
    enderror
    -0.50
    LookAnd
    -0.49
    POSITIVE LOGITS
    ligg
    0.56
    rawDesc
    0.56
    AddTagHelper
    0.54
    >//
    0.52
     getItemId
    0.51
     चीज़ों
    0.51
    softc
    0.50
    PullParser
    0.50
    Rhestr
    0.50
     genomen
    0.50
    Activations Density 13.831%

    No Known Activations