© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15830
    Prev
    Next
    INDEX
    Explanations

    words related to items you can buy, ingest, or interact with in the world, and also to find references to feelings of ill-being or unease

    oai_token-act-pair · gemini-2.0-flash

    Eating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     eating
    -0.79
     resourceCulture
    -0.75
    featureID
    -0.71
     snippetHide
    -0.70
     eats
    -0.68
     eat
    -0.66
    Eating
    -0.66
     Eating
    -0.66
     CreateTagHelper
    -0.65
     intptr
    -0.64
    POSITIVE LOGITS
     prévenir
    0.61
     Morgen
    0.56
    changeable
    0.55
     Tag
    0.55
    блон
    0.54
     inner
    0.54
    ruppe
    0.53
    ראי
    0.52
    İstinadlar
    0.52
     mu
    0.52
    Activations Density 44.444%

    No Known Activations