© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5470
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express the possibility of something

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Waray
    -0.51
    LabelTagHelper
    -0.50
     layui
    -0.50
    antaine
    -0.50
    BeginContext
    -0.49
    ProgressHUD
    -0.46
    ederos
    -0.45
     capito
    -0.45
    xase
    -0.44
    fois
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.66
     disambiguazione
    0.63
    cshtml
    0.60
     Cycling
    0.58
    Бахар
    0.56
    addColumn
    0.55
    WebVitals
    0.54
     dissolving
    0.54
    Begriffsklä
    0.54
    ResumeLayout
    0.54
    Activations Density 3.995%

    No Known Activations