© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12478
    Prev
    Next
    INDEX
    Explanations

    instructions for cooking

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming keywords

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

    instructions and recipes

    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
     itſelf
    -0.59
     ſhe
    -0.58
     houſe
    -0.54
    OrderDetails
    -0.53
     themſelves
    -0.53
     myſelf
    -0.51
     Majefty
    -0.50
    кож
    -0.50
     ruas
    -0.50
     murale
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.67
    ApiModelProperty
    0.65
    脚注の使い方
    0.63
     cherchés
    0.61
    saraba
    0.61
    CPtr
    0.59
     PublicKey
    0.58
    complexContent
    0.57
    مصادر
    0.57
    WithIOException
    0.57
    Activations Density 1.734%

    No Known Activations