© 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. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12393
    Prev
    Next
    INDEX
    Explanations

    words and symbols commonly used in scientific or statistical writing such as table, relative error, equations and other formulas

    oai_token-act-pair · gemini-2.0-flash

    Statistical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    AutoScaleMode
    -0.62
    NUMX
    -0.60
     allAfrica
    -0.60
     surla
    -0.59
    ISupport
    -0.57
     يتيمه
    -0.57
     mergeFrom
    -0.56
     الحره
    -0.55
     observable
    -0.55
    iric
    -0.54
    POSITIVE LOGITS
    omitempty
    0.56
    原始内容存档于
    0.50
     ExecuteAsync
    0.46
     OnInit
    0.45
    WebVitals
    0.45
    Хьажоргаш
    0.42
    esModule
    0.40
     nakalista
    0.39
     capita
    0.38
     nauki
    0.37
    Activations Density 3.065%

    No Known Activations