© 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. 3643
    Prev
    Next
    INDEX
    Explanations

    word sequences related to probability calculations

    oai_token-act-pair · gemini-2.0-flash

    Probability of picking letters

    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
     betweenstory
    -0.71
     تضيفلها
    -0.64
     inaugur
    -0.63
     molding
    -0.61
    Personensuche
    -0.61
     emig
    -0.60
     eject
    -0.60
    FXML
    -0.60
    Diweddarwch
    -0.59
     steering
    -0.59
    POSITIVE LOGITS
    NewUrlParser
    0.61
     lure
    0.61
    ági
    0.60
     связано
    0.57
     challenge
    0.55
    useNewUrlParser
    0.54
     tremble
    0.54
    enumi
    0.54
     howl
    0.54
     sob
    0.52
    Activations Density 14.288%

    No Known Activations