© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4806
    Prev
    Next
    INDEX
    Explanations

    causal relationships involving "due to", "driven by", or "stems from".

    oai_token-act-pair · gemini-2.0-flash

    causation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     ContentValues
    -0.73
    BufferException
    -0.68
    IntoConstraints
    -0.67
    adaptiveStyles
    -0.67
    mybatisplus
    -0.66
    ftagPool
    -0.66
     EconPapers
    -0.65
     pinulongan
    -0.63
     Plaster
    -0.63
     Pingback
    -0.62
    POSITIVE LOGITS
    <bos>
    2.33
    '
    0.75
    ’
    0.71
    def
    0.60
     The
    0.60
    <h2>
    0.60
    -
    0.59
     are
    0.54
    The
    0.54
    ↵
    0.54
    Activations Density 2.315%

    No Known Activations