© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8545
    Prev
    Next
    INDEX
    Explanations

    words related to packet switching and time synchronization

    oai_token-act-pair · gemini-2.0-flash

    networking data transfer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     صوتيه
    -0.71
    KURZBESCHREIBUNG
    -0.69
    RenderAtEndOf
    -0.68
    richTextPanel
    -0.64
    Webpack
    -0.63
     Belk
    -0.63
    olesterol
    -0.63
    mlink
    -0.63
    vember
    -0.61
     للاسماء
    -0.59
    POSITIVE LOGITS
    참고
    0.39
     UnityEngine
    0.36
     SM
    0.35
    Base
    0.35
     AssemblyTitle
    0.35
    庇
    0.34
    DJANGO
    0.34
    дец
    0.34
     PAM
    0.34
    UT
    0.33
    Activations Density 2.362%

    No Known Activations