© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6478
    Prev
    Next
    INDEX
    Explanations

    the word "executive" but also finds words that have "ess" as a suffix, as well as some action words.

    oai_token-act-pair · gemini-2.0-flash

    executive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Amic
    -0.71
     istr
    -0.58
     zlo
    -0.57
    bership
    -0.56
    mallows
    -0.56
     SPARK
    -0.55
     zar
    -0.55
    ppé
    -0.55
    ESS
    -0.55
    almaz
    -0.54
    POSITIVE LOGITS
    <bos>
    1.57
    bootstrapcdn
    0.94
     the
    0.81
    MigrationBuilder
    0.78
     насељу
    0.73
    (!__
    0.71
     enfans
    0.70
     gloire
    0.69
    Geplaatst
    0.69
    rungsseite
    0.68
    Activations Density 1.660%

    No Known Activations