© 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. 10011
    Prev
    Next
    INDEX
    Explanations

    the word "can" and contractions using "can"

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "can"

    np_token-act-pair-logits · gpt-4o-mini

    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_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
    Known
    -0.52
    Datuak
    -0.51
     Known
    -0.50
    EnableWeb
    -0.50
    zecz
    -0.49
    known
    -0.45
    stantial
    -0.45
     armb
    -0.44
    Rescue
    -0.44
     Gabri
    -0.44
    POSITIVE LOGITS
    Autoritní
    0.93
    webElementXpaths
    0.81
    ConstraintMaker
    0.77
    EndContext
    0.71
    GenerationType
    0.71
    makeConstraints
    0.71
    省市镇
    0.69
    aarrggbb
    0.69
    elemField
    0.68
     gynhyrchwyd
    0.68
    Activations Density 0.281%

    No Known Activations