© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5616
    Prev
    Next
    INDEX
    Explanations

    legal or scientific references

    oai_token-act-pair · gemini-2.0-flash

    legal, military contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    webElementXpaths
    -0.77
    adaptiveStyles
    -0.73
     ModelExpression
    -0.68
    -------------</
    -0.64
     saites
    -0.61
     ExecuteAsync
    -0.60
     isInitialized
    -0.55
    SharedCtor
    -0.54
    complexType
    -0.52
    sizeCache
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.68
     carab
    0.65
     թվական
    0.59
    skem
    0.57
    extAlignment
    0.57
     epig
    0.56
    TagHelper
    0.55
    mator
    0.55
     تانيه
    0.53
     trainers
    0.52
    Activations Density 1.662%

    No Known Activations