© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5703
    Prev
    Next
    INDEX
    Explanations

    information about the Hamburg U-Bahn public transportation system, especially its stations and network

    oai_token-act-pair · gemini-2.0-flash

    technical or coding terminology

    np_token-act-pair-logits · gpt-4o-mini

    German place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    mybatisplus
    -0.63
    HostException
    -0.52
    neden
    -0.51
    ttemberg
    -0.50
    SOUNDBITE
    -0.49
    IVEREF
    -0.49
    UnknownFields
    -0.48
     progress
    -0.48
     asyncio
    -0.47
    ŚCI
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.71
    ">${
    0.52
     opérés
    0.51
     PEM
    0.50
     ExecuteAsync
    0.48
    pexpr
    0.48
    étation
    0.47
     Hush
    0.46
    MessageTagHelper
    0.45
     Ause
    0.45
    Activations Density 1.054%

    No Known Activations