© 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. 13033
    Prev
    Next
    INDEX
    Explanations

    the word "direct" and related legal terms like "brief" and "hence"

    oai_token-act-pair · gemini-2.0-flash

    direct

    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
    ]--;
    -1.21
    RegressionTest
    -1.07
     auffi
    -0.97
     Meksiku
    -0.96
     myſelf
    -0.94
    RenderAtEndOf
    -0.93
     ſch
    -0.91
     uſed
    -0.90
     doubtnut
    -0.84
     Initialise
    -0.84
    POSITIVE LOGITS
    <bos>
    0.59
     
    0.59
     ";
    0.54
    м
    0.54
    {}".
    0.52
    й
    0.50
     "]
    0.49
     by
    0.49
     pretty
    0.49
     of
    0.49
    Activations Density 1.402%

    No Known Activations