© 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. 2842
    Prev
    Next
    INDEX
    Explanations

    numerical data related to amounts of people, money, or things

    oai_token-act-pair · gemini-2.0-flash

    large numbers

    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
    setVerticalGroup
    -0.80
    脚注の使い方
    -0.70
     unknownFields
    -0.62
    WithMany
    -0.61
    lihood
    -0.61
     صوتيه
    -0.58
    ableness
    -0.56
     noDo
    -0.56
    aneity
    -0.55
     Donation
    -0.53
    POSITIVE LOGITS
    LookAnd
    0.61
     AssemblyProduct
    0.60
    <bos>
    0.57
     ModelExpression
    0.56
    pol
    0.54
     AssemblyTitle
    0.53
    ⓘ
    0.50
    Buildable
    0.47
    เศษ
    0.46
    #
    0.45
    Activations Density 4.669%

    No Known Activations