© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4687
    Prev
    Next
    INDEX
    Explanations

    the word "developed"

    oai_token-act-pair · gemini-2.0-flash

    develop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     develop
    -2.59
     developed
    -2.38
     developing
    -2.30
     develops
    -2.27
    develop
    -2.23
     Develop
    -2.20
     DEVELOP
    -2.19
    Develop
    -2.11
    developed
    -2.08
    developing
    -2.08
    POSITIVE LOGITS
     InputDecoration
    0.66
     chattering
    0.65
     getItemCount
    0.64
     confetti
    0.64
     LXXX
    0.63
     Volga
    0.63
     sendMessage
    0.63
     lepto
    0.61
     Valence
    0.60
     Carboniferous
    0.60
    Activations Density 0.563%

    No Known Activations