© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5663
    Prev
    Next
    INDEX
    Explanations

    code blocks in Java or similar languages, particularly focusing on try statements and curly braces

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    antMatchers
    -0.56
     архивлан
    -0.50
     mxArray
    -0.48
    Rüyada
    -0.48
    istoitu
    -0.48
    ছে
    -0.47
     invokingState
    -0.47
     Che
    -0.47
    findpost
    -0.47
    RegistryLite
    -0.47
    POSITIVE LOGITS
     InputDecoration
    0.75
    expandindo
    0.61
     lenker
    0.61
    glLoadIdentity
    0.56
    ioutil
    0.55
     Sadie
    0.54
     تانيه
    0.52
     Eccles
    0.52
    msgTypes
    0.52
     slat
    0.51
    Activations Density 0.728%

    No Known Activations