© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9795
    Prev
    Next
    INDEX
    Explanations

    words related to food, especially ingredients and dishes

    oai_token-act-pair · gemini-2.0-flash

    food descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     spice
    -1.35
    Spice
    -1.32
     Spice
    -1.29
    Pepper
    -1.16
     Pepper
    -1.15
    spice
    -1.14
     spicy
    -1.09
     pepper
    -1.08
    pepper
    -1.05
     Spicy
    -1.05
    POSITIVE LOGITS
    Hé
    0.47
     Gleaner
    0.45
     Absch
    0.45
    новниш
    0.44
     flakes
    0.44
     كومونز
    0.43
     MainAxisSize
    0.43
    tow
    0.42
    ambito
    0.41
    ọi
    0.40
    Activations Density 1.321%

    No Known Activations