© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9667
    Prev
    Next
    INDEX
    Explanations

    words and concepts preceded by "well-"

    oai_token-act-pair · gemini-2.0-flash

    well-known

    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
    enumi
    -0.89
     оригіналу
    -0.71
    enumii
    -0.68
     فريبيس
    -0.62
    WebVitals
    -0.60
     يتيمه
    -0.59
    orija
    -0.59
    AndEndTag
    -0.59
     مشين
    -0.59
     BoxDecoration
    -0.57
    POSITIVE LOGITS
    reg
    0.48
    stě
    0.48
    ichel
    0.45
     travelled
    0.44
    read
    0.43
     παρου
    0.43
     attended
    0.42
    ItemBackground
    0.42
    Reg
    0.42
     read
    0.41
    Activations Density 0.300%

    No Known Activations