© 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. 8001
    Prev
    Next
    INDEX
    Explanations

    words related to construction, with a weaker association for belief or importance

    oai_token-act-pair · gemini-2.0-flash

    build

    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
     the
    -0.79
     also
    -0.65
     V
    -0.57
     a
    -0.57
     B
    -0.56
     several
    -0.56
     specialised
    -0.56
     some
    -0.56
     Con
    -0.54
     many
    -0.54
    POSITIVE LOGITS
    ValueStyle
    1.08
     Référence
    0.95
     Vikipedi
    0.93
    Portail
    0.93
    Datuak
    0.93
    ibatis
    0.92
     Signalez
    0.91
     >=",
    0.91
     unknownFields
    0.88
     viewType
    0.88
    Activations Density 1.257%

    No Known Activations