© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13936
    Prev
    Next
    INDEX
    Explanations

    scientific articles and references in particular

    oai_token-act-pair · gemini-2.0-flash

    Finance and legal topics

    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
     adonan
    -0.42
    velo
    -0.36
    InitStruct
    -0.35
    پور
    -0.35
     Ver
    -0.35
    asko
    -0.35
     да
    -0.33
     reino
    -0.33
     сда
    -0.33
    ftagPool
    -0.33
    POSITIVE LOGITS
    Rüyada
    0.74
    fjspx
    0.68
     myſelf
    0.66
    ndose
    0.66
     Holes
    0.65
     Efq
    0.64
     insuffisamment
    0.64
     zirc
    0.63
    localctx
    0.63
    ſelf
    0.62
    Activations Density 4.081%

    No Known Activations