© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12985
    Prev
    Next
    INDEX
    Explanations

    seemingly random short fragments of text that include multiple words, often with a mix of standard language, technical terms, or unusual capitalization.

    oai_token-act-pair · gemini-2.0-flash

    Internet forum excerpts

    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
    <bos>
    -0.64
    ROIT
    -0.60
    VIAF
    -0.56
    Portale
    -0.55
     Baillargeon
    -0.54
    roek
    -0.52
     Packs
    -0.52
    וויק
    -0.52
     상세
    -0.52
    țională
    -0.49
    POSITIVE LOGITS
     chronologically
    0.38
     verrez
    0.34
    WithMany
    0.34
     tentativo
    0.34
    ="@+
    0.34
    contentLoaded
    0.33
    EditorBrowsable
    0.33
    الدرا
    0.33
    ⓧ
    0.33
    NameInMap
    0.32
    Activations Density 1.265%

    No Known Activations