© 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. 12683
    Prev
    Next
    INDEX
    Explanations

    negative prefixes and references to the COVID-19 pandemic

    oai_token-act-pair · gemini-2.0-flash

    non

    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
    Portale
    -0.67
    apimachinery
    -0.56
    bitField
    -0.56
    invokeLater
    -0.54
     tokenId
    -0.54
    ApiController
    -0.50
    impan
    -0.49
    migrationBuilder
    -0.49
    herme
    -0.48
    DebuggerStep
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.61
     '\\;'
    0.58
     lenker
    0.55
     للمعارف
    0.53
     chng
    0.49
    Judges
    0.48
    RTDA
    0.47
    usermodel
    0.46
    UTERS
    0.44
    angliski
    0.44
    Activations Density 6.747%

    No Known Activations