© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12227
    Prev
    Next
    INDEX
    Explanations

    the word "is" and other forms of "be"

    oai_token-act-pair · gemini-2.0-flash

    becoming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     MyBatis
    -0.48
    MethodManager
    -0.48
    throw
    -0.48
    lead
    -0.47
    NewUrlParser
    -0.46
     kurzer
    -0.44
     BorderRadius
    -0.44
     asal
    -0.44
    TagHelpers
    -0.43
    riers
    -0.42
    POSITIVE LOGITS
     being
    0.86
     gaining
    0.73
    brainly
    0.71
     coming
    0.70
     changing
    0.67
     developing
    0.66
     facing
    0.66
     becoming
    0.65
     catching
    0.65
     Савезне
    0.65
    Activations Density 1.492%

    No Known Activations