© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9351
    Prev
    Next
    INDEX
    Explanations

    text that talks about seasons and months of the year, especially around holidays

    oai_token-act-pair · gemini-2.0-flash

    dates and times

    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
    EndGlobalSection
    -0.65
    Примітки
    -0.60
     AspNetCore
    -0.59
     насељу
    -0.58
    TemporalType
    -0.57
     Roskov
    -0.55
    NameInMap
    -0.55
    riezmann
    -0.53
    __':
    -0.52
     AssemblyProduct
    -0.52
    POSITIVE LOGITS
     Comprometido
    0.60
     mergeFrom
    0.58
     asiatique
    0.55
     selatan
    0.55
     becauſe
    0.54
     honneur
    0.54
    yaf
    0.54
     tremp
    0.53
     totul
    0.53
     élas
    0.53
    Activations Density 5.437%

    No Known Activations