© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13140
    Prev
    Next
    INDEX
    Explanations

    words related to fonts and text editing

    oai_token-act-pair · gemini-2.0-flash

    source code or editing software

    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
     fidélité
    -0.47
     nationales
    -0.45
    CloseOperation
    -0.43
     freg
    -0.43
     contributo
    -0.42
     مخطط
    -0.42
    elry
    -0.41
    ադ
    -0.41
     démocr
    -0.41
    コツ
    -0.41
    POSITIVE LOGITS
     initComponents
    0.79
    yntaxException
    0.73
     kasarigan
    0.73
     propOrder
    0.60
    isContained
    0.60
    Portale
    0.59
    MLLoader
    0.58
    SharedCtor
    0.57
     Assignee
    0.56
    épend
    0.56
    Activations Density 3.372%

    No Known Activations