© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5303
    Prev
    Next
    INDEX
    Explanations

    titles and historical periods related to Japanese political history

    oai_token-act-pair · gemini-2.0-flash

    empires and emperors

    np_max-act-logits · 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
     imperial
    -1.66
     Imperial
    -1.58
    Imperial
    -1.43
     emperor
    -1.38
     Empire
    -1.38
     empire
    -1.29
     Emperor
    -1.28
    imperial
    -1.27
    Empire
    -1.24
    Emperor
    -1.23
    POSITIVE LOGITS
    degradable
    0.46
     Cama
    0.44
    AfterEach
    0.43
     Karak
    0.42
    itab
    0.41
    nance
    0.41
    npmjs
    0.40
     Knut
    0.40
     Malam
    0.40
    lably
    0.40
    Activations Density 1.572%

    No Known Activations