© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10590
    Prev
    Next
    INDEX
    Explanations

    restaurant reviews, especially looking for descriptions of food and ingredients.

    oai_token-act-pair · gemini-2.0-flash

    restaurant reviews/menus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     nakalista
    -0.66
     AssemblyProduct
    -0.58
     المعيارى
    -0.57
    herzog
    -0.53
    ########.
    -0.52
     Ashland
    -0.52
    ariConfig
    -0.52
     gustaba
    -0.50
     rosse
    -0.50
    شهاد
    -0.50
    POSITIVE LOGITS
     wireType
    0.68
    withIdentifier
    0.57
    ValueGeneration
    0.57
     newOwner
    0.57
    omitempty
    0.56
    makeConstraints
    0.52
    CDCl
    0.51
    JKLM
    0.50
     Warm
    0.50
    SharedDtor
    0.50
    Activations Density 0.823%

    No Known Activations