© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12803
    Prev
    Next
    INDEX
    Explanations

    cooking recipes or kitchen tool discussions

    oai_token-act-pair · gemini-2.0-flash

    food-related terms

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

    preceding nouns

    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
    AndEndTag
    -0.90
     يتيمه
    -0.81
    verwijspagina
    -0.73
     Réponses
    -0.68
    لينكات
    -0.67
    ագրություններ
    -0.66
    elemField
    -0.65
    ⓘ
    -0.64
     noDo
    -0.61
     Lightboxes
    -0.60
    POSITIVE LOGITS
    цездатний
    0.52
     food
    0.51
     super
    0.46
     USB
    0.43
    food
    0.41
    答案
    0.40
    PRNewswire
    0.40
     plan
    0.40
    Frequency
    0.40
     maso
    0.40
    Activations Density 1.488%

    No Known Activations