© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 741
    Prev
    Next
    INDEX
    Explanations

    statistical relationships and study results in scientific publications.

    oai_token-act-pair · gemini-2.0-flash

    association

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     association
    -2.27
     associate
    -1.99
    association
    -1.98
    associate
    -1.95
     Association
    -1.93
     associations
    -1.91
    Association
    -1.90
    ASSOCI
    -1.84
     associ
    -1.83
     associating
    -1.83
    POSITIVE LOGITS
    phemy
    0.60
     Engage
    0.53
    THEORY
    0.51
    feas
    0.51
     Générale
    0.50
     Meld
    0.50
    andafter
    0.49
     CONCEPT
    0.49
    ecio
    0.49
     hybrid
    0.48
    Activations Density 14.713%

    No Known Activations