© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11467
    Prev
    Next
    INDEX
    Explanations

    instances of "can be" followed by a verb, particularly in mathematical or scientific contexts.

    oai_token-act-pair · gemini-2.0-flash

    can

    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
     nahilalakip
    -0.99
    complexContent
    -0.91
    Hauptartikel
    -0.90
    новништво
    -0.90
     chi̍t
    -0.90
    Tembelea
    -0.88
     propOrder
    -0.85
    ReusableCell
    -0.84
    ագրություններ
    -0.84
    Datuak
    -0.84
    POSITIVE LOGITS
     serve
    0.54
    <bos>
    0.52
    cent
    0.46
     serves
    0.45
    -
    0.43
     M
    0.43
    IDENTITY
    0.41
     play
    0.40
     stat
    0.40
     plays
    0.40
    Activations Density 7.646%

    No Known Activations