© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16189
    Prev
    Next
    INDEX
    Explanations

    words frequently found in legal documents related to judgment and remuneration

    oai_token-act-pair · gemini-2.0-flash

    Money and compensation

    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
    HtmlAttribute
    -0.61
    tagHelperRunner
    -0.59
     onCancelled
    -0.58
     EconPapers
    -0.54
    CppMethod
    -0.52
    grà
    -0.51
    ProgressHUD
    -0.51
     ✭✭
    -0.49
    TableHead
    -0.48
    AFX
    -0.48
    POSITIVE LOGITS
     دیکھیے
    0.60
    verwijspagina
    0.52
     détaillée
    0.51
     MainAxisSize
    0.50
    idavit
    0.49
    utivo
    0.49
    parties
    0.49
     "..\..\
    0.48
     "..\..\..\
    0.48
    gds
    0.48
    Activations Density 16.657%

    No Known Activations