© 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. 12396
    Prev
    Next
    INDEX
    Explanations

    passages that express opinions or arguments

    oai_token-act-pair · gemini-2.0-flash

    negations and contractions

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

    words with "n't"

    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
    too
    -0.69
    Too
    -0.66
     TOO
    -0.64
     too
    -0.64
     Too
    -0.64
    IsContent
    -0.55
     demasi
    -0.55
    وصلات
    -0.55
    TOO
    -0.52
     initComponents
    -0.52
    POSITIVE LOGITS
     doesn
    0.73
     isn
    0.73
     InputDecoration
    0.67
     Isn
    0.65
     Doesn
    0.63
    Doesn
    0.62
     didn
    0.60
     onlyOwner
    0.60
     OMIT
    0.60
     hasn
    0.59
    Activations Density 5.164%

    No Known Activations