© 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. 11931
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically parts of C code involving network protocols

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     ostrich
    -0.74
     Zoro
    -0.74
     salomon
    -0.73
     virgins
    -0.69
     Mahomet
    -0.69
     Indoch
    -0.67
     calum
    -0.67
     Sarm
    -0.67
     Deuter
    -0.66
     incest
    -0.66
    POSITIVE LOGITS
     name
    0.71
     set
    0.71
     new
    0.68
     get
    0.66
     noDo
    0.66
     start
    0.66
     type
    0.66
     On
    0.66
     text
    0.65
     stop
    0.65
    Activations Density 18.132%

    No Known Activations