© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3108
    Prev
    Next
    INDEX
    Explanations

    substrings and keywords in code files and configuration files

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    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
     CURIAM
    -0.60
    apunov
    -0.58
     CURLOPT
    -0.49
    AnimationsModule
    -0.46
     UNAM
    -0.42
     automatiques
    -0.42
    WidgetItem
    -0.41
    adə
    -0.41
     menyus
    -0.40
     veng
    -0.40
    POSITIVE LOGITS
    rawDesc
    0.65
    pagesize
    0.60
    Tembelea
    0.58
    AutoField
    0.57
    fieldId
    0.57
    hasMany
    0.56
    tonode
    0.56
    RefNanny
    0.55
    isEnd
    0.55
     maxWidth
    0.54
    Activations Density 6.925%

    No Known Activations