© 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. 15586
    Prev
    Next
    INDEX
    Explanations

    phrases that express subjectivity, importance, or need

    oai_token-act-pair · gemini-2.0-flash

    Thing

    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
     thing
    -0.60
    мум
    -0.48
    のは
    -0.46
     &$
    -0.46
    のが
    -0.42
     connexes
    -0.42
     heisst
    -0.42
     års
    -0.41
    parentElement
    -0.41
     дело
    -0.41
    POSITIVE LOGITS
     occaf
    0.80
     Shakspeare
    0.80
    IsMutable
    0.78
     OFDb
    0.76
     fubject
    0.75
     Jefus
    0.74
    IntoConstraints
    0.73
     EconPapers
    0.73
    webElement
    0.72
     @"/
    0.70
    Activations Density 6.092%

    No Known Activations