© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10255
    Prev
    Next
    INDEX
    Explanations

    questions starting with any form of "to be"

    oai_token-act-pair · gemini-2.0-flash

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    astéroïdes
    -0.77
     Caster
    -0.75
     Pilate
    -0.75
     acacia
    -0.75
     betyr
    -0.74
     banknotes
    -0.73
    HCR
    -0.72
     flocc
    -0.71
     skär
    -0.69
     nemico
    -0.69
    POSITIVE LOGITS
    <bos>
    0.96
      
    0.62
     have
    0.62
    maxcdn
    0.60
     of
    0.59
    й
    0.59
     get
    0.58
    न
    0.58
     we
    0.57
     are
    0.57
    Activations Density 0.773%

    No Known Activations