© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6294
    Prev
    Next
    INDEX
    Explanations

    mentions of places to eat and people that work there

    oai_token-act-pair · gemini-2.0-flash

    restaurants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     restaurant
    -2.14
     Restaurant
    -1.86
    Restaurant
    -1.83
    restaurant
    -1.80
     restaurants
    -1.77
     RESTAURANT
    -1.69
    RESTAUR
    -1.56
     Restaurants
    -1.55
     restaurante
    -1.45
    Restaurants
    -1.45
    POSITIVE LOGITS
     *)__
    0.68
     للاسماء
    0.67
     CreateTagHelper
    0.66
    يكب
    0.54
     оригіналу
    0.54
    ListItemIcon
    0.53
     createSprite
    0.52
     traditionnels
    0.52
    脚注の使い方
    0.52
    addCriterion
    0.52
    Activations Density 0.680%

    No Known Activations