© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9260
    Prev
    Next
    INDEX
    Explanations

    code snippets including functions in Java or similar languages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     {
    -1.36
    {
    -1.20
    ){
    -1.06
    (){
    -1.05
    "){
    -1.02
    /**
    -0.98
    ">
    -0.98
    '){
    -0.90
     {{\
    -0.85
    {{\
    -0.82
    POSITIVE LOGITS
    =()
    0.71
     חיצוניים
    0.65
    BeginContext
    0.64
     OMITBAD
    0.63
    ])))
    0.63
    },[])
    0.63
     AssemblyCulture
    0.60
    Välislingid
    0.59
    CodedInputStream
    0.59
     يتيمه
    0.59
    Activations Density 3.116%

    No Known Activations