© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10529
    Prev
    Next
    INDEX
    Explanations

    connections from one part to another using prepositions

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     coppia
    -0.53
     yourselves
    -0.52
     protoimpl
    -0.49
     ddelweddau
    -0.49
     conseguenza
    -0.48
    /*---
    -0.48
     Rex
    -0.46
    AccessorTable
    -0.45
     Lennox
    -0.45
    T
    -0.45
    POSITIVE LOGITS
    ":{
    0.58
    $")
    0.56
    Архівовано
    0.55
     }>
    0.54
    *)((
    0.53
    MeasureSpec
    0.53
    ')],
    0.53
    hooting
    0.53
    ){$
    0.52
    }());
    0.52
    Activations Density 1.232%

    No Known Activations