© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6156
    Prev
    Next
    INDEX
    Explanations

    various discourse markers and connector words, possibly identifying sentiment and subjective statements.

    oai_token-act-pair · gemini-2.0-flash

    nouns or identifiers related to programming

    np_token-act-pair-logits · gpt-4o-mini

    online shopping/reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Erstellt
    -0.49
    FormTagHelper
    -0.43
    יד
    -0.42
    Искәрмәләр
    -0.42
    вя
    -0.41
    ション
    -0.40
    Ifc
    -0.40
     _
    -0.39
    ---*/
    -0.39
    CJK
    -0.38
    POSITIVE LOGITS
    parsedMessage
    0.92
     autorytatywna
    0.92
     متعلقه
    0.83
    adaptiveStyles
    0.77
     purpoſe
    0.76
     initComponents
    0.74
    TagMode
    0.73
     iſt
    0.73
     myſelf
    0.73
     ſon
    0.71
    Activations Density 0.926%

    No Known Activations