© 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. 14207
    Prev
    Next
    INDEX
    Explanations

    the word 'armed' and words associated with groups

    oai_token-act-pair · gemini-2.0-flash

    armed

    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
     Jefus
    -1.59
     myſelf
    -1.56
     pleaſure
    -1.56
     themſelves
    -1.51
     itſelf
    -1.48
     purpoſe
    -1.46
     Theſe
    -1.45
     Diſ
    -1.44
     reaſon
    -1.43
     houſe
    -1.43
    POSITIVE LOGITS
     dunia
    0.73
     her
    0.73
     connus
    0.71
     he
    0.71
     the
    0.71
     it
    0.71
     as
    0.69
     of
    0.69
     so
    0.68
     my
    0.68
    Activations Density 1.811%

    No Known Activations