© 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. 8461
    Prev
    Next
    INDEX
    Explanations

    the word "main" and, to a lesser extent, words used to describe a race

    oai_token-act-pair · gemini-2.0-flash

    main

    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
    <bos>
    -0.78
    ########.
    -0.52
     Azad
    -0.51
     aks
    -0.50
     Référence
    -0.48
    MigrationBuilder
    -0.48
     يتيمه
    -0.48
    lexus
    -0.47
     matrimonial
    -0.46
     Réponses
    -0.46
    POSITIVE LOGITS
     auroit
    0.86
     ainfi
    0.86
     féminine
    0.84
     étoient
    0.84
     Monfieur
    0.82
     plufieurs
    0.81
     feroit
    0.80
     duquel
    0.78
     avoient
    0.77
     quæ
    0.77
    Activations Density 2.669%

    No Known Activations