© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15049
    Prev
    Next
    INDEX
    Explanations

    sentences discussing the causes and effects of something

    oai_token-act-pair · gemini-2.0-flash

    cause

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    rrggbb
    -0.54
     fleste
    -0.54
    protoimpl
    -0.53
     "..\..\..\
    -0.52
    TypedDataSet
    -0.51
     saites
    -0.49
     connues
    -0.48
    letoe
    -0.48
     出版
    -0.48
    이터
    -0.48
    POSITIVE LOGITS
    Билгалдахарш
    0.63
     للمعارف
    0.59
    Искәрмәләр
    0.57
    perity
    0.52
     loss
    0.52
    Ț
    0.51
     Misch
    0.50
    SequentialGroup
    0.50
     unhealthy
    0.49
    Partager
    0.49
    Activations Density 3.311%

    No Known Activations