© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10045
    Prev
    Next
    INDEX
    Explanations

    discourse markers such as "there", "however", and "in"

    oai_token-act-pair · gemini-2.0-flash

    there

    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
    ⓧ
    -1.26
    AnchorStyles
    -1.05
    Autoritní
    -1.03
    RTEE
    -1.03
    WithIOException
    -0.96
     تضيفلها
    -0.94
    IsMutable
    -0.94
     protoimpl
    -0.94
    Portale
    -0.93
    GEBURTSDATUM
    -0.93
    POSITIVE LOGITS
    ↵↵
    0.84
    The
    0.82
    In
    0.81
    However
    0.79
     However
    0.76
    Moreover
    0.75
    When
    0.75
     The
    0.71
     In
    0.71
    ↵
    0.70
    Activations Density 4.789%

    No Known Activations