© 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. 14549
    Prev
    Next
    INDEX
    Explanations

    the conditional form of the verbs "would," "vas," "pourrais"

    oai_token-act-pair · gemini-2.0-flash

    Online conversations

    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
     betweenstory
    -0.60
    存于互联网档案馆
    -0.56
    ViewImports
    -0.53
     nakalista
    -0.53
    GAP
    -0.51
     Chwiliwch
    -0.51
    的面
    -0.50
    IsContent
    -0.50
    ScopeManager
    -0.49
    üm
    -0.49
    POSITIVE LOGITS
     will
    0.91
    Will
    0.89
    will
    0.87
     Will
    0.78
    Será
    0.77
     WILL
    0.69
     zullen
    0.69
    <bos>
    0.68
    WILL
    0.67
    DockStyle
    0.67
    Activations Density 1.728%

    No Known Activations