© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12520
    Prev
    Next
    INDEX
    Explanations

    words followed by what appear to be hexadecimal codes or numbers

    oai_token-act-pair · gemini-2.0-flash

    few

    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
     المعيارى
    -0.80
    ,:);
    -0.77
    脚注の使い方
    -0.73
    "</
    -0.72
     InputDecoration
    -0.72
     استنادى
    -0.71
     ISNI
    -0.71
    fromnode
    -0.71
    ientôt
    -0.69
    ,:]
    -0.69
    POSITIVE LOGITS
     three
    0.79
     four
    0.74
    Three
    0.71
     five
    0.71
    three
    0.69
     seven
    0.65
     six
    0.64
    Four
    0.63
     to
    0.61
    five
    0.59
    Activations Density 2.130%

    No Known Activations