© 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. 4094
    Prev
    Next
    INDEX
    Explanations

    words related to dental health, especially tooth erosion and remineralization.

    oai_token-act-pair · gemini-2.0-flash

    dental and oral health

    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
    __':
    -0.75
    migrationBuilder
    -0.70
    libft
    -0.61
    routeProvider
    -0.61
    contentLoaded
    -0.60
    parseFrom
    -0.55
    providedIn
    -0.55
    Искәрмәләр
    -0.54
     AssemblyVersion
    -0.54
    лтемелер
    -0.53
    POSITIVE LOGITS
     pronouns
    0.56
    ungeons
    0.52
    Sound
    0.50
     Sound
    0.50
    AndEndTag
    0.50
    ImageField
    0.49
     EconPapers
    0.46
     Обо
    0.46
     opérateurs
    0.45
     SOUND
    0.45
    Activations Density 2.175%

    No Known Activations