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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15089
    Prev
    Next
    INDEX
    Explanations

    code snippets from Protocol Buffers, including references to Proto3, unit tests, messages, enums, and internal data structures.

    oai_token-act-pair · gemini-2.0-flash

    Protobuf protocol

    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
     Proto
    -1.81
     Protocol
    -1.81
     PROTO
    -1.79
     protocol
    -1.79
     proto
    -1.78
     Protocols
    -1.72
    Proto
    -1.70
     Eth
    -1.67
     protocols
    -1.66
     eth
    -1.66
    POSITIVE LOGITS
    expandindo
    0.57
    AnimationsModule
    0.56
    verwijspagina
    0.54
     Zjednoc
    0.53
    Ārējās
    0.53
     Vle
    0.52
     nahilalakip
    0.52
    DockStyle
    0.51
     Vereinig
    0.51
    ModelBuilder
    0.49
    Activations Density 3.296%

    No Known Activations