© 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. 13286
    Prev
    Next
    INDEX
    Explanations

    words with an emotional charge which often have to do with issues of morality, support, race.

    oai_token-act-pair · gemini-2.0-flash

    support

    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
    DockStyle
    -0.95
     "..\..\
    -0.81
    ✨:
    -0.81
     "..\..\..\
    -0.80
    drawiam
    -0.75
    
    -0.75
     BoxFit
    -0.75
    Personendaten
    -0.73
     autorytatywna
    -0.73
    UnusedPrivate
    -0.73
    POSITIVE LOGITS
     (!(
    0.61
    (*(
    0.57
    ongyang
    0.57
     idéia
    0.57
     pressão
    0.57
    ane
    0.54
    ::_
    0.54
     -=
    0.53
     puis
    0.53
     Investigaciones
    0.52
    Activations Density 3.661%

    No Known Activations