© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7143
    Prev
    Next
    INDEX
    Explanations

    references to historical events and people, especially those involving conflict, oppression, and social hierarchy.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     виправивши
    -0.56
    EDEFAULT
    -0.52
     musia
    -0.51
     muft
    -0.49
     timings
    -0.48
     giù
    -0.47
     jsPsych
    -0.46
    marginVertical
    -0.46
     Eben
    -0.46
     setw
    -0.45
    POSITIVE LOGITS
    timewa
    0.68
     الحره
    0.64
    StoryboardSegue
    0.63
    DockStyle
    0.59
    icrous
    0.56
     accepting
    0.53
    \{\\
    0.53
    zegor
    0.52
     undergoing
    0.51
    itarios
    0.51
    Activations Density 3.157%

    No Known Activations