© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3151
    Prev
    Next
    INDEX
    Explanations

    words that are often found in restaurant reviews, especially dishes and ingredients

    oai_token-act-pair · gemini-2.0-flash

    culinary terms related to dishes

    np_token-act-pair-logits · gpt-4o-mini

    restaurant food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    enumi
    -0.56
     esternos
    -0.56
    TintMode
    -0.54
     organisée
    -0.52
    исленность
    -0.52
     kasarigan
    -0.51
    Tikang
    -0.50
     snippetHide
    -0.50
    penup
    -0.48
     Grecs
    -0.48
    POSITIVE LOGITS
    styleType
    0.61
    ometrial
    0.56
    omla
    0.52
    thod
    0.50
    ulg
    0.49
    .*")]
    0.48
    iffen
    0.46
    ecore
    0.46
    şiv
    0.46
    uel
    0.46
    Activations Density 0.573%

    No Known Activations