© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13394
    Prev
    Next
    INDEX
    Explanations

    the word "haven"

    oai_token-act-pair · gemini-2.0-flash

    haven

    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
    Negative Logits
     myſelf
    -2.05
     Efq
    -1.98
     Theſe
    -1.86
     purpoſe
    -1.86
     Monfieur
    -1.80
     pleaſure
    -1.78
     themſelves
    -1.77
     himſelf
    -1.77
     Jefus
    -1.75
     poffible
    -1.71
    POSITIVE LOGITS
     
    1.16
    <eos>
    1.06
    n
    0.90
    ,
    0.90
     (
    0.90
     in
    0.88
     [
    0.87
     and
    0.85
     E
    0.82
    3
    0.82
    Activations Density 1.317%

    No Known Activations