© 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. 14074
    Prev
    Next
    INDEX
    Explanations

    numerical data including IP addresses and other identifiers, especially with very low values

    oai_token-act-pair · gemini-2.0-flash

    (

    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
    
    -0.76
    RegressionTest
    -0.54
    expandindo
    -0.54
     виправивши
    -0.47
     Walkover
    -0.45
    RTEE
    -0.43
    Tembelea
    -0.43
     comunista
    -0.42
     provinciale
    -0.41
     Constructors
    -0.41
    POSITIVE LOGITS
    VersionUID
    0.77
    SequentialGroup
    0.75
    '][]
    0.74
    MENAFN
    0.67
    enumi
    0.65
     للمعارف
    0.65
     UIAlert
    0.65
    存于互联网档案馆
    0.65
    StoryboardSegue
    0.64
    saraba
    0.63
    Activations Density 18.704%

    No Known Activations