© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    the word "fluid".

    oai_token-act-pair · gemini-2.0-flash

    fluid

    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
    ↵
    -0.72
    ↵↵
    -0.69
     P
    -0.69
     an
    -0.68
     ris
    -0.65
     K
    -0.65
    .
    -0.63
     A
    -0.62
     T
    -0.61
     The
    -0.61
    POSITIVE LOGITS
     myſelf
    1.80
     itſelf
    1.73
     pleaſure
    1.53
     ſmall
    1.51
     ſeveral
    1.50
     himſelf
    1.49
     becauſe
    1.49
     faſt
    1.47
     themſelves
    1.45
     reaſon
    1.45
    Activations Density 2.114%

    No Known Activations