© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 114
    Prev
    Next
    INDEX
    Explanations

    technical terms describing experimental procedures in biology

    oai_token-act-pair · gemini-2.0-flash

    validate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Paglinawan
    -0.75
     للاسماء
    -0.73
     Италијани
    -0.68
    enterOuterAlt
    -0.66
    Vidite
    -0.63
     Biôgrafia
    -0.63
    MigrationBuilder
    -0.59
    NewUrlParser
    -0.59
     resourceCulture
    -0.59
    gulier
    -0.58
    POSITIVE LOGITS
    consider
    0.49
     direito
    0.43
    tahu
    0.42
     mirage
    0.42
    边
    0.41
    achte
    0.41
    سياسي
    0.40
     bọn
    0.40
    vor
    0.40
     capaces
    0.40
    Activations Density 21.787%

    No Known Activations