© 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. 15400
    Prev
    Next
    INDEX
    Explanations

    capitalized abbreviations, proper nouns, and brand names, especially of American origin.

    oai_token-act-pair · gemini-2.0-flash

    place names or organizations

    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
     estekak
    -0.67
    UnusedPrivate
    -0.60
    IUrlHelper
    -0.52
     ujednoznacz
    -0.49
     disambiguazione
    -0.48
     <<<<<<<<<<<<<<
    -0.48
    rungsseite
    -0.48
     figliu
    -0.47
    AccessorTable
    -0.47
    __':
    
    -0.46
    POSITIVE LOGITS
    itative
    0.40
    itation
    0.39
    uary
    0.36
    tainment
    0.36
    hedrals
    0.35
    ateness
    0.35
    ularity
    0.35
    τυχ
    0.34
    atrician
    0.34
    bourhood
    0.34
    Activations Density 9.099%

    No Known Activations