© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9248
    Prev
    Next
    INDEX
    Explanations

    text about chefs, food preparation and official residences

    oai_token-act-pair · gemini-2.0-flash

    chefs and cooking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     CreateTagHelper
    -0.76
    tvguidetime
    -0.75
     незавершена
    -0.66
     autorytatywna
    -0.59
     uintptr
    -0.57
    ophanes
    -0.53
    endphp
    -0.52
    ፩
    -0.52
    timedia
    -0.49
    thschild
    -0.49
    POSITIVE LOGITS
    LayoutPanel
    0.57
    ObjectModel
    0.53
     consultato
    0.51
    ⓧ
    0.51
     Allociné
    0.51
    ευ
    0.50
    setVerticalGroup
    0.49
     المعيارى
    0.49
    farwyddwr
    0.47
    ramienta
    0.46
    Activations Density 2.115%

    No Known Activations