© 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. 12306
    Prev
    Next
    INDEX
    Explanations

    sentence fragments, often prepositions, conjunctions and punctuation, in code and scientific documents

    oai_token-act-pair · gemini-2.0-flash

    technical terms and references

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

    say "the"

    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
     hän
    -0.58
    StructEnd
    -0.52
     we
    -0.49
     rayures
    -0.47
     że
    -0.46
    peutic
    -0.46
    mbito
    -0.45
     they
    -0.44
     sẻ
    -0.43
     run
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.84
     the
    0.79
    drawal
    0.79
    LabelTagHelper
    0.79
    ſelf
    0.79
    ReusableCell
    0.78
     Jefus
    0.75
     Monfieur
    0.74
     pngtree
    0.72
     reaſon
    0.71
    Activations Density 8.341%

    No Known Activations