© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7171
    Prev
    Next
    INDEX
    Explanations

    text describing the legislative process around controversial bills

    oai_token-act-pair · gemini-2.0-flash

    legislation/bills

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     passing
    -2.11
     passed
    -2.09
     passes
    -1.98
     pass
    -1.98
     Passing
    -1.84
    Passing
    -1.79
    pass
    -1.75
     Passed
    -1.74
    passed
    -1.74
     passage
    -1.74
    POSITIVE LOGITS
    Gweler
    0.59
    IContainer
    0.58
    AutoScale
    0.54
    tvguidetime
    0.54
    expandindo
    0.53
    RefNanny
    0.52
    gdx
    0.50
    stridium
    0.50
    Hochspringen
    0.49
    
    0.49
    Activations Density 0.732%

    No Known Activations