© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14388
    Prev
    Next
    INDEX
    Explanations

    language related to sales and discounts

    oai_token-act-pair · gemini-2.0-flash

    variations of "is" or "are"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     uintptr
    -0.50
    up
    -0.42
    hen
    -0.41
     -
    -0.40
    IElement
    -0.40
    iner
    -0.39
     "
    -0.39
    int
    -0.37
     Glas
    -0.37
    хал
    -0.37
    POSITIVE LOGITS
     poffible
    0.98
     Efq
    0.98
     myſelf
    0.95
     itſelf
    0.94
     ſtate
    0.92
     whoſe
    0.92
     חיצוניים
    0.92
    WebVitals
    0.92
     purpoſe
    0.91
     deſt
    0.91
    Activations Density 3.720%

    No Known Activations