© 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. 6248
    Prev
    Next
    INDEX
    Explanations

    words associated with electrical and mechanical engineering with a focus on emergency backup power.

    oai_token-act-pair · gemini-2.0-flash

    buildings and engineering

    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
    GraphicsUnit
    -0.56
     للمعارف
    -0.53
    ⓘ
    -0.53
    TabIndex
    -0.50
    Là
    -0.48
    principalTable
    -0.48
     Showers
    -0.47
     otel
    -0.46
     Fence
    -0.46
     Heiz
    -0.46
    POSITIVE LOGITS
    例文帳に追加
    0.56
    actionMode
    0.56
    tonsoft
    0.55
     jadx
    0.53
    TSCA
    0.52
     Réponses
    0.50
    unyai
    0.50
    showthread
    0.50
    ворю
    0.49
    ЧИТА
    0.49
    Activations Density 2.553%

    No Known Activations