© 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. 5960
    Prev
    Next
    INDEX
    Explanations

    c code defining directories or files

    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
     The
    -0.69
     On
    -0.68
     For
    -0.68
     We
    -0.68
     Some
    -0.68
     Whether
    -0.67
     By
    -0.67
    WebServlet
    -0.66
     In
    -0.65
     Home
    -0.65
    POSITIVE LOGITS
    saraba
    0.50
     PTR
    0.44
     CHECKBOX
    0.41
     affari
    0.40
     IndexPath
    0.39
     PRT
    0.39
     RQ
    0.38
     PDB
    0.38
     étoit
    0.38
     ""){
    0.38
    Activations Density 9.227%

    No Known Activations