© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13010
    Prev
    Next
    INDEX
    Explanations

    the word "can" and other words that frequently accompany 'can'.

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     can
    -0.72
     may
    -0.68
     يتيمه
    -0.62
    can
    -0.58
     do
    -0.54
    may
    -0.54
     might
    -0.53
     kann
    -0.52
    Mar
    -0.51
     CAN
    -0.50
    POSITIVE LOGITS
     CURIAM
    0.97
    niająca
    0.69
     Résultats
    0.68
    ImageContext
    0.66
     lautet
    0.65
    neath
    0.65
    phosa
    0.64
     disponibilités
    0.64
     متعلقه
    0.63
     fuselage
    0.63
    Activations Density 0.436%

    No Known Activations