© 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. 12506
    Prev
    Next
    INDEX
    Explanations

    date-like patterns of numbers, mixed with other phrases, links, etc

    oai_token-act-pair · gemini-2.0-flash

    Blog posts and articles

    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
     bonnes
    -0.46
     '*')
    -0.44
     good
    -0.44
     capitolo
    -0.42
     noires
    -0.41
     dimentic
    -0.41
    ResponseCode
    -0.41
     préc
    -0.40
     pauvres
    -0.40
     trouva
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    0.91
     Normdatei
    0.89
    GeneratedValue
    0.86
     nakalista
    0.83
    StoreMessageInfo
    0.78
    IUrlHelper
    0.78
    InSection
    0.77
     &___
    0.77
    setVerticalGroup
    0.77
    DeleteBehavior
    0.76
    Activations Density 19.008%

    No Known Activations