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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9908
    Prev
    Next
    INDEX
    Explanations

    descriptions of food and beverages, including alcoholic and non-alcoholic drinks, and food ingredients

    oai_token-act-pair · gemini-2.0-flash

    fruit

    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
    MLLoader
    -0.74
     Réponses
    -0.61
    ɵɵ
    -0.60
    LookAnd
    -0.53
    __':
    -0.52
    UnusedPrivate
    -0.52
    ubon
    -0.51
    elemField
    -0.51
     onOptions
    -0.50
    хьтан
    -0.49
    POSITIVE LOGITS
     fruit
    0.72
     Orange
    0.71
     Paglinawan
    0.71
     pomegranate
    0.68
     orange
    0.68
     pineapple
    0.68
     Pineapple
    0.68
    Orange
    0.67
     ORANGE
    0.66
     apple
    0.65
    Activations Density 1.290%

    No Known Activations