© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3167
    Prev
    Next
    INDEX
    Explanations

    mentions of seafood

    oai_token-act-pair · gemini-2.0-flash

    phrases related to fish

    np_token-act-pair-logits · gpt-4o-mini

    fish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     propOrder
    -0.55
    edoc
    -0.48
     fisk
    -0.47
     rusa
    -0.47
    matchCondition
    -0.46
     molle
    -0.43
     podio
    -0.42
     oprot
    -0.42
    Boli
    -0.41
     gear
    -0.40
    POSITIVE LOGITS
     lenker
    0.77
     CreateTagHelper
    0.69
     utafitiHapana
    0.62
    interopRequire
    0.62
     للمعارف
    0.61
     Drapeau
    0.58
     onAnimation
    0.57
    MessageTagHelper
    0.56
    ukkah
    0.56
     Bourgoin
    0.55
    Activations Density 1.269%

    No Known Activations