© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 248
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that are related to methods, research studies, and data analysis

    oai_token-act-pair · gemini-2.0-flash

    management planning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    +#+#
    -0.63
    <bos>
    -0.54
    ukone
    -0.48
    PerformLayout
    -0.47
    endregion
    -0.46
    mtd
    -0.43
    ंदीखरीदारी
    -0.43
    nos
    -0.43
     ru
    -0.42
     versus
    -0.42
    POSITIVE LOGITS
     виправивши
    0.60
    vrigt
    0.60
    ürger
    0.57
     prouve
    0.57
     isSet
    0.56
    Referencies
    0.55
     başına
    0.55
    帖最后由
    0.55
     shroud
    0.54
     metav
    0.54
    Activations Density 18.278%

    No Known Activations