© 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. 6973
    Prev
    Next
    INDEX
    Explanations

    the letters "ac" at the starts of words

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "Ac"

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

    Ac

    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
     Réponses
    -0.65
    hyrchwyd
    -0.61
    principalTable
    -0.58
    Rüyada
    -0.54
    onViewCreated
    -0.52
    SharedCtor
    -0.50
    webElementXpaths
    -0.47
    transQ
    -0.47
    IsPostBack
    -0.46
    hysema
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.57
    DotNetBar
    0.55
    elemField
    0.55
     Xunit
    0.54
    GraphicsUnit
    0.52
    prefixer
    0.51
     noDo
    0.50
    bootstrapcdn
    0.49
    CompoundButton
    0.47
    Bronnen
    0.46
    Activations Density 0.471%

    No Known Activations