© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12446
    Prev
    Next
    INDEX
    Explanations

    mentions of the past tense of "to have"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "had" and "have"

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

    had/having

    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
    PreferredItem
    -0.75
     autorytatywna
    -0.74
     disambiguazione
    -0.71
    expandindo
    -0.67
    ValueStyle
    -0.65
    stdc
    -0.64
    AsUp
    -0.64
    IntoConstraints
    -0.63
     Normdatei
    -0.62
    Numerology
    -0.62
    POSITIVE LOGITS
     a
    0.77
     the
    0.65
     an
    0.58
     bı
    0.55
     unequal
    0.52
     irré
    0.52
    gare
    0.49
     Schrift
    0.48
     these
    0.47
     his
    0.47
    Activations Density 1.529%

    No Known Activations