© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5103
    Prev
    Next
    INDEX
    Explanations

    the title "Prime Minister"

    oai_token-act-pair · gemini-2.0-flash

    Prime

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     nahilalakip
    -1.03
     betweenstory
    -1.00
     myſelf
    -0.97
     endregion
    -0.96
     Monfieur
    -0.95
     Efq
    -0.94
    WithIOException
    -0.93
     themſelves
    -0.93
    bitField
    -0.91
     Normdatei
    -0.90
    POSITIVE LOGITS
     m
    0.34
     s
    0.34
     D
    0.31
     matéria
    0.30
     Mo
    0.30
    وس
    0.30
    ског
    0.29
     r
    0.29
     Tim
    0.28
     humedad
    0.28
    Activations Density 0.404%

    No Known Activations