© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9677
    Prev
    Next
    INDEX
    Explanations

    the word "the" and other very common words

    oai_token-act-pair · gemini-2.0-flash

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     his
    -0.52
     the
    -0.51
     an
    -0.50
     The
    -0.49
     B
    -0.48
     a
    -0.48
    льга
    -0.47
     her
    -0.46
    <eos>
    -0.45
     M
    -0.42
    POSITIVE LOGITS
    awtextra
    1.00
     itſelf
    0.97
    MigrationBuilder
    0.94
     Monfieur
    0.89
     myſelf
    0.89
     Efq
    0.89
     EconPapers
    0.87
     ModelExpression
    0.85
     Anſ
    0.84
    ſelf
    0.84
    Activations Density 2.257%

    No Known Activations