© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12247
    Prev
    Next
    INDEX
    Explanations

    the word "too", sometimes along with other words nearby

    oai_token-act-pair · gemini-2.0-flash

    too

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     unknownFields
    -0.63
     Too
    -0.63
     too
    -0.62
    too
    -0.57
    ')):
    -0.57
    GRect
    -0.56
     numerus
    -0.56
    TOO
    -0.55
    AsUp
    -0.54
     TOO
    -0.54
    POSITIVE LOGITS
     purpoſe
    0.76
     myſelf
    0.75
     Shakspeare
    0.73
     houſe
    0.66
     Shaksp
    0.66
    tvguidetime
    0.65
     mihi
    0.65
     ſch
    0.63
     pleaſure
    0.63
     Monfieur
    0.62
    Activations Density 1.530%

    No Known Activations