© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7870
    Prev
    Next
    INDEX
    Explanations

    phrases containing "same" that indicate similarity or the superlative "best."

    oai_token-act-pair · gemini-2.0-flash

    same

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     AssemblyTitle
    -0.72
     lenker
    -0.59
     pioggia
    -0.58
     présidenti
    -0.58
     BorderSide
    -0.58
    PreferredItem
    -0.55
     quæ
    -0.55
     étoient
    -0.55
     fédé
    -0.52
    CPtr
    -0.52
    POSITIVE LOGITS
     consultato
    0.57
    rxjs
    0.54
     person
    0.53
    HtmlAttribute
    0.53
    orama
    0.51
    poni
    0.51
    IContainer
    0.50
    AutoresizingMask
    0.50
    mony
    0.49
     kind
    0.48
    Activations Density 2.634%

    No Known Activations