© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 5335
    Prev
    Next
    INDEX
    Explanations

    the word "designated."

    oai_token-act-pair · gemini-2.0-flash

    designating places/events

    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
    InjectAttribute
    -1.09
    ]<<"
    -1.06
    GraphicsUnit
    -1.02
     AssemblyCulture
    -0.98
     snippetHide
    -0.97
     Bourgoin
    -0.96
    ]--;
    -0.95
    expandindo
    -0.95
     setuptools
    -0.92
     pinulongan
    -0.92
    POSITIVE LOGITS
    <em>
    0.84
    an
    0.80
     that
    0.72
    <strong>
    0.72
    .
    0.68
     of
    0.66
     
    0.65
    The
    0.65
     as
    0.65
     the
    0.65
    Activations Density 1.768%

    No Known Activations