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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2777
    Prev
    Next
    INDEX
    Explanations

    mentions of a "cave"

    oai_token-act-pair · gemini-2.0-flash

    caves and tunnels

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tunnels
    -1.16
     cave
    -1.16
     Cave
    -1.14
     tunnel
    -1.11
     Tunnel
    -1.08
    Cave
    -1.06
     caves
    -1.05
     hole
    -1.00
    cave
    -1.00
     tunneling
    -0.98
    POSITIVE LOGITS
    bak
    0.51
    chara
    0.50
     Dek
    0.49
    routeProvider
    0.47
    Counter
    0.45
    Tembelea
    0.44
    ală
    0.44
    kiat
    0.43
     Counter
    0.43
    itattu
    0.43
    Activations Density 1.922%

    No Known Activations