© 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. 4439
    Prev
    Next
    INDEX
    Explanations

    calculations related to prime factors or divisibility.

    oai_token-act-pair · gemini-2.0-flash

    prime factors

    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
     '\\;'
    -0.66
     infrastructure
    -0.57
     Erişim
    -0.56
    sphase
    -0.54
    GEBURTS
    -0.53
     ICA
    -0.52
    Ecotoxicity
    -0.52
    didSet
    -0.52
    ftagPool
    -0.52
     Infrastructure
    -0.51
    POSITIVE LOGITS
    oznam
    0.62
     الرياضيه
    0.55
    شهاد
    0.54
    ConstraintMaker
    0.51
    TestingModule
    0.51
    ">—
    0.51
     defaultstate
    0.49
    Espèce
    0.47
     divisors
    0.47
     שוליים
    0.47
    Activations Density 16.236%

    No Known Activations