© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14400
    Prev
    Next
    INDEX
    Explanations

    phrases about a person's education and origin

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ErrIntOverflow
    -0.65
    yntaxException
    -0.64
     wireType
    -0.59
    CodedInputStream
    -0.58
     TextAlign
    -0.58
     Meksiku
    -0.58
     ModelExpression
    -0.58
    AnimationsModule
    -0.54
     WaitForSeconds
    -0.54
    neté
    -0.54
    POSITIVE LOGITS
     "").
    0.50
     põ
    0.49
     tege
    0.49
     mäng
    0.48
     inimes
    0.47
     meil
    0.47
     maksi
    0.46
     tõ
    0.46
    Хьажоргаш
    0.46
     "")
    
    0.46
    Activations Density 0.093%

    No Known Activations