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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8449
    Prev
    Next
    INDEX
    Explanations

    words relating to the making of history and the act of creating through effort.

    oai_token-act-pair · gemini-2.0-flash

    variants of the word "history"

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

    history

    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
    yntaxException
    -0.55
    acyjne
    -0.53
    AttributeSet
    -0.51
    ตอน
    -0.49
    orteur
    -0.48
     ReSharper
    -0.48
    djangoproject
    -0.46
     CharSequence
    -0.46
    Configurer
    -0.46
     législ
    -0.46
    POSITIVE LOGITS
     history
    2.39
    history
    2.06
     History
    1.91
     HISTORY
    1.83
    History
    1.80
    HISTORY
    1.63
     histories
    1.48
     sejarah
    1.45
     historia
    1.41
    歴史
    1.39
    Activations Density 1.467%

    No Known Activations