© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6961
    Prev
    Next
    INDEX
    Explanations

    code snippets in go

    oai_token-act-pair · gemini-2.0-flash

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AppDelegate
    -0.63
    CppCodeGen
    -0.61
     defaultstate
    -0.60
     StringTokenizer
    -0.60
     steak
    -0.59
    ResponseWriter
    -0.59
    SpringRunner
    -0.57
     Morin
    -0.55
    interopRequire
    -0.55
     Jehovah
    -0.55
    POSITIVE LOGITS
     Paglinawan
    0.69
     industriels
    0.62
     traités
    0.57
    ondissement
    0.54
    RegressionTest
    0.54
     dieux
    0.53
     périodes
    0.52
    ⓧ
    0.52
     automatiques
    0.52
     női
    0.50
    Activations Density 2.200%

    No Known Activations