© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15304
    Prev
    Next
    INDEX
    Explanations

    descriptions of declines or reductions in physical quantities or states, as well as submissive or deferential gestures

    oai_token-act-pair · gemini-2.0-flash

    "low"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     raised
    -0.94
     Raised
    -0.91
     raising
    -0.86
     Raising
    -0.84
     Raise
    -0.81
    raising
    -0.81
    raised
    -0.80
     raise
    -0.79
    high
    -0.79
    Raising
    -0.78
    POSITIVE LOGITS
     low
    2.42
     Low
    2.13
    Low
    2.06
    low
    1.95
     LOW
    1.91
     lower
    1.74
     lowest
    1.72
    LOW
    1.69
    低
    1.63
     低
    1.43
    Activations Density 4.374%

    No Known Activations