© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5538
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sewing and purchasing fabric, especially in the past

    oai_token-act-pair · gemini-2.0-flash

    terms related to sewing and fabric

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

    retail stores

    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
    CppCodeGen
    -0.65
    SourceChecksum
    -0.60
    sales
    -0.59
    衛門
    -0.59
    Sales
    -0.57
     sales
    -0.55
     Sales
    -0.54
    ScopeManager
    -0.53
    nextToken
    -0.52
     Armada
    -0.52
    POSITIVE LOGITS
     chain
    0.63
     समीक्षक
    0.63
     chains
    0.62
     Chain
    0.59
    __":
    0.56
    __":
    0.55
    Chain
    0.54
    invokeLater
    0.53
    SequentialGroup
    0.52
     places
    0.52
    Activations Density 1.373%

    No Known Activations