© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4458
    Prev
    Next
    INDEX
    Explanations

    single uppercase letters, especially when part of common acronyms or initialisms or email addresses

    oai_token-act-pair · gemini-2.0-flash

    Acronyms and abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    FOOTNOTES
    -0.60
    èdia
    -0.58
    íncia
    -0.53
     artificiales
    -0.50
     romántica
    -0.48
     NKC
    -0.48
     MSA
    -0.48
     Anfitrión
    -0.46
     LCCN
    -0.46
     Expédié
    -0.46
    POSITIVE LOGITS
    idom
    0.58
     CAC
    0.56
     LUMP
    0.56
     SIG
    0.54
     MOP
    0.54
     DAP
    0.54
     Pis
    0.53
     Cic
    0.53
     Gib
    0.53
     EST
    0.53
    Activations Density 3.504%

    No Known Activations