© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9927
    Prev
    Next
    INDEX
    Explanations

    C++ template code, especially relating to boost metaprogramming library

    oai_token-act-pair · gemini-2.0-flash

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Normdatei
    -0.72
     BitmapFactory
    -0.71
     @"/
    -0.71
     Wiktionnaire
    -0.71
    +#+
    -0.71
    Rohy
    -0.71
    #+#
    -0.69
    клопе
    -0.68
     مشين
    -0.67
    NUMX
    -0.67
    POSITIVE LOGITS
     nakalista
    0.68
    iedy
    0.54
    HasAnnotation
    0.54
     fronte
    0.52
     screen
    0.50
    択
    0.46
     comprendere
    0.45
     strana
    0.45
     procedere
    0.45
    InvalidProtocol
    0.44
    Activations Density 1.342%

    No Known Activations