© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14767
    Prev
    Next
    INDEX
    Explanations

    sentences containing the words "everything", "another", "thing", or forms of the verb "to be" with limited context.

    oai_token-act-pair · gemini-2.0-flash

    Everything

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Everything
    -0.68
     everyone
    -0.68
     Everyone
    -0.64
    Everything
    -0.64
     everything
    -0.63
    Everyone
    -0.63
    everything
    -0.60
    everyone
    -0.56
     everybody
    -0.56
     Everybody
    -0.54
    POSITIVE LOGITS
    MLLoader
    0.85
     <=",
    0.79
     nakalista
    0.77
     Normdatei
    0.76
    MMV
    0.76
    TypedDataSet
    0.75
    RegressionTest
    0.75
    ThroughAttribute
    0.75
    canestro
    0.74
    -------------</
    0.73
    Activations Density 6.391%

    No Known Activations