© 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. 12189
    Prev
    Next
    INDEX
    Explanations

    the letter "D" appearing either on its own or as the beginning of a word, often in the context of code or programming languages.

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'd' or 'D'

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

    d

    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
     tiền
    -0.46
    rcParams
    -0.44
    segno
    -0.43
    sacrifice
    -0.43
    logii
    -0.40
    Volunteer
    -0.40
     industriale
    -0.40
    kani
    -0.40
     passagers
    -0.39
     pubblicità
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.75
     resourceCulture
    0.69
     препратки
    0.68
    ModelSerializer
    0.66
     iprot
    0.66
    MetaObject
    0.65
    SOUNDBITE
    0.61
    addWidget
    0.60
    ImageContext
    0.60
     ModelExpression
    0.59
    Activations Density 1.296%

    No Known Activations