© 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. 15981
    Prev
    Next
    INDEX
    Explanations

    words relating to middle eastern cuisine

    oai_token-act-pair · gemini-2.0-flash

    Describing various cuisines' food

    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
    EditorBrowsable
    -0.60
    contentLoaded
    -0.59
    writeFieldEnd
    -0.57
     MyBatis
    -0.54
     météoro
    -0.53
    lighet
    -0.53
    $/,
    -0.52
    awtextra
    -0.52
    发表于
    -0.51
    WithIOException
    -0.51
    POSITIVE LOGITS
     moschino
    0.55
     Muro
    0.54
     JpaRepository
    0.54
     combust
    0.54
     Monfieur
    0.53
     becauſe
    0.53
     Euripides
    0.53
     Carthag
    0.53
     myſelf
    0.50
     Majefty
    0.50
    Activations Density 0.720%

    No Known Activations