© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14636
    Prev
    Next
    INDEX
    Explanations

    descriptive words that are in some way positive

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ⓧ
    -0.76
    tagHelperRunner
    -0.69
    Autoritní
    -0.68
    RegressionTest
    -0.68
     MessageBoxIcon
    -0.67
    GEBURTSDATUM
    -0.66
    AsUp
    -0.65
    ScopeManager
    -0.64
     Majefty
    -0.64
    ίδι
    -0.62
    POSITIVE LOGITS
    IFUL
    0.52
     تضيفلها
    0.49
    ÉM
    0.49
    liction
    0.49
    <>("
    0.47
    Hochspringen
    0.46
     propOrder
    0.46
     himo
    0.45
    viewBox
    0.45
     Référence
    0.44
    Activations Density 0.492%

    No Known Activations