© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10369
    Prev
    Next
    INDEX
    Explanations

    the word "used" when indicating a past experience or habit

    oai_token-act-pair · gemini-2.0-flash

    used

    np_max-act-logits · gemini-2.0-flash

    the word "used"

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    UIViewController
    -0.53
    AndEndTag
    -0.52
     resourceCulture
    -0.52
     kter
    -0.50
    rizona
    -0.49
    jupiter
    -0.48
     welches
    -0.47
    zbęd
    -0.47
     useParams
    -0.47
     useContext
    -0.47
    POSITIVE LOGITS
     to
    1.09
     وتسجيلات
    0.62
    Personensuche
    0.61
    Dislikes
    0.57
    ⓧ
    0.56
    prüche
    0.54
     indisponible
    0.53
     ddelweddau
    0.50
     متعلقه
    0.49
    cuadro
    0.48
    Activations Density 0.229%

    No Known Activations