© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10778
    Prev
    Next
    INDEX
    Explanations

    the phrase "New York Times"

    oai_token-act-pair · gemini-2.0-flash

    New

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    StoryboardSegue
    -0.73
    jskiej
    -0.58
    DoubleQuotes
    -0.52
     esternos
    -0.51
     صوتيه
    -0.50
    indak
    -0.49
     Czy
    -0.48
    stateProvider
    -0.48
     doGet
    -0.47
    tetur
    -0.47
    POSITIVE LOGITS
     تضيفلها
    0.61
    writeFieldEnd
    0.58
    styleType
    0.54
    ValueStyle
    0.54
    ंदीखरीदारी
    0.52
    Geograf
    0.47
    sub
    0.45
    tifie
    0.45
     MonoBehaviour
    0.45
    findpost
    0.45
    Activations Density 0.366%

    No Known Activations