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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 607
    Prev
    Next
    INDEX
    Explanations

    text related to cheese and cheesesteaks, and less strongly other foods

    oai_token-act-pair · gemini-2.0-flash

    Cheese and milk

    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
     mergeFrom
    -0.65
     unknownFields
    -0.57
    UnitTesting
    -0.56
    يميديا
    -0.56
    retweeted
    -0.53
    //</
    -0.52
     >=",
    -0.51
     ProtoMessage
    -0.50
    ArgsConstructor
    -0.50
    memoized
    -0.49
    POSITIVE LOGITS
    oa̍t
    0.59
     affichés
    0.57
    ConstraintMaker
    0.54
    SourceChecksum
    0.52
    bekah
    0.52
    tafel
    0.52
    awtextra
    0.51
     rendus
    0.50
    ValueGeneration
    0.49
     interactiva
    0.48
    Activations Density 1.269%

    No Known Activations