© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9948
    Prev
    Next
    INDEX
    Explanations

    the word "be" or parts of words containing the letters "be"

    oai_token-act-pair · gemini-2.0-flash

    be

    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
    be
    -2.92
    BE
    -2.00
    Be
    -1.70
     BE
    -1.51
     Be
    -1.43
     be
    -1.36
    bes
    -1.16
    bej
    -1.16
    bek
    -1.01
    beh
    -1.00
    POSITIVE LOGITS
    homonymie
    0.79
    IndentedString
    0.76
    SBATCH
    0.75
    Hentet
    0.74
    ISupport
    0.73
     الحره
    0.73
    ReusableCell
    0.72
     Réponses
    0.72
    WriteTagHelper
    0.72
    ThroughAttribute
    0.71
    Activations Density 0.531%

    No Known Activations