© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6442
    Prev
    Next
    INDEX
    Explanations

    words that signify historical and significant change

    oai_token-act-pair · gemini-2.0-flash

    downhill

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     flavors
    -0.95
     flavor
    -0.90
     flavored
    -0.89
     flavours
    -0.84
     flavour
    -0.84
     flavoured
    -0.83
     Flavor
    -0.82
    ImageContext
    -0.79
    flavor
    -0.74
     tasted
    -0.67
    POSITIVE LOGITS
     downhill
    0.77
     decline
    0.75
     downg
    0.65
     Decline
    0.59
    dow
    0.58
     reg
    0.56
     downgrade
    0.54
     rot
    0.53
     decay
    0.52
    decline
    0.52
    Activations Density 0.573%

    No Known Activations