© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5490
    Prev
    Next
    INDEX
    Explanations

    words that create a sense of disruption or turning point in a story

    oai_token-act-pair · gemini-2.0-flash

    temporal conjunctions

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

    when

    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
    ThroughAttribute
    -0.85
     defaultstate
    -0.80
    ագրություններ
    -0.73
    قایناقلار
    -0.68
    ProcessEvent
    -0.62
    tinyos
    -0.59
    Diweddarwch
    -0.57
     createSprite
    -0.57
    HasAnnotation
    -0.57
    DebuggerNonUser
    -0.56
    POSITIVE LOGITS
     when
    2.31
    when
    1.92
     quando
    1.77
     cuando
    1.72
    When
    1.63
     WHEN
    1.58
     When
    1.57
     когда
    1.53
     lorsqu
    1.47
     lorsque
    1.45
    Activations Density 2.867%

    No Known Activations