© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10976
    Prev
    Next
    INDEX
    Explanations

    nouns followed by possessive suffixes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    stdafx
    -0.41
    यार
    -0.40
     Moskau
    -0.39
    .
    -0.39
     I
    -0.39
    l
    -0.39
    setw
    -0.39
    stdarg
    -0.39
     setw
    -0.38
    ↵↵
    -0.38
    POSITIVE LOGITS
    ngdoc
    0.96
    Sucesor
    0.86
    üyada
    0.85
     Majefty
    0.80
    MENAFN
    0.80
     Paglinawan
    0.77
    expandindo
    0.77
    Rüyada
    0.77
     auffi
    0.74
     архивлан
    0.72
    Activations Density 3.092%

    No Known Activations