© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11083
    Prev
    Next
    INDEX
    Explanations

    restaurant names and food items, particularly in the context of reviews

    oai_token-act-pair · gemini-2.0-flash

    restaurant reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    rend
    -0.49
    HomeComponent
    -0.48
     getItemId
    -0.47
    kod
    -0.47
    onna
    -0.47
     >=",
    -0.46
    τητα
    -0.45
    ,:),
    -0.45
    mach
    -0.45
     *);
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.66
     EconPapers
    0.58
    Portale
    0.57
    PerformLayout
    0.55
    titleMargin
    0.54
    KURZBESCHREIBUNG
    0.54
    principalTable
    0.54
     diep
    0.54
    Datuak
    0.53
    FormTagHelper
    0.53
    Activations Density 0.285%

    No Known Activations