© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16046
    Prev
    Next
    INDEX
    Explanations

    subjective opinions about a person, where the person is referred to as "he"

    oai_token-act-pair · gemini-2.0-flash

    knowledge, ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     invités
    -0.51
    dibly
    -0.47
     occupé
    -0.45
     Scroll
    -0.45
     smě
    -0.43
     Railway
    -0.43
    option
    -0.42
     supérieurs
    -0.41
    hæ
    -0.40
    agama
    -0.40
    POSITIVE LOGITS
    twimg
    0.90
     الرياضيه
    0.89
    Datuak
    0.89
    initComponents
    0.88
    GenerationType
    0.86
     مشين
    0.85
    SourceChecksum
    0.83
    Geplaatst
    0.81
    makeConstraints
    0.81
     كومونز
    0.79
    Activations Density 1.579%

    No Known Activations