© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16359
    Prev
    Next
    INDEX
    Explanations

    capitalized words, particularly names of people, places, organizations, and works of art

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    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
     createState
    -0.48
    MemoryWarning
    -0.42
    0
    -0.40
     proceeds
    -0.39
    TextBoxColumn
    -0.38
    CheckedChanged
    -0.38
    TabStop
    -0.37
     manufacture
    -0.36
     economies
    -0.36
     TestBed
    -0.36
    POSITIVE LOGITS
    SharedCtor
    0.54
     Мексичка
    0.53
    UrlResolution
    0.52
    Susie
    0.51
    Tina
    0.51
     chré
    0.50
    ItemBackground
    0.50
     roulant
    0.50
    ñora
    0.48
     Lyra
    0.47
    Activations Density 25.488%

    No Known Activations