© 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. 7868
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases about value and worth, often in a business context

    oai_token-act-pair · gemini-2.0-flash

    value

    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
     value
    -3.25
    value
    -2.88
     Value
    -2.84
    Value
    -2.70
     VALUE
    -2.59
    VALUE
    -2.27
     valeur
    -2.19
     values
    -2.14
     Values
    -2.03
     valore
    -1.92
    POSITIVE LOGITS
    CloseOperation
    0.48
     riktig
    0.46
     perdere
    0.46
    ViewStyle
    0.44
    iciais
    0.44
    ulkan
    0.43
     Vaz
    0.43
    propTypes
    0.41
     JScrollPane
    0.41
    Tazama
    0.41
    Activations Density 2.733%

    No Known Activations