© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8095
    Prev
    Next
    INDEX
    Explanations

    instructions related to making a cocktail

    oai_token-act-pair · gemini-2.0-flash

    alcoholic beverages

    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
    хьтан
    -0.61
    findpost
    -0.61
    ChildScrollView
    -0.58
    DoubleQuotes
    -0.57
    XmlEnum
    -0.56
    transQ
    -0.54
    HasForeignKey
    -0.54
    ApiController
    -0.52
    DockStyle
    -0.49
     Protobuf
    -0.49
    POSITIVE LOGITS
     glasses
    0.65
     bicchiere
    0.63
     drinking
    0.60
     sip
    0.60
     verres
    0.58
     beverage
    0.57
     drinkers
    0.57
    Drinking
    0.56
    osé
    0.56
    Cheers
    0.56
    Activations Density 0.743%

    No Known Activations