© 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. 15564
    Prev
    Next
    INDEX
    Explanations

    words and numbers associated with academic institutions/programs and accreditation.

    oai_token-act-pair · gemini-2.0-flash

    Education/Universities

    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
     Meksiku
    -0.48
     withal
    -0.47
     Boiling
    -0.45
    Personensuche
    -0.44
     gunpowder
    -0.44
     perfons
    -0.44
     dryness
    -0.44
     DOWNVOTE
    -0.43
     Petrol
    -0.42
    Хьажоргаш
    -0.42
    POSITIVE LOGITS
    出版年
    0.73
    CEC
    0.63
    CSA
    0.63
    SpringBootTest
    0.61
    GPA
    0.58
    ICAS
    0.56
    SLP
    0.56
    MSU
    0.55
    PRNewswire
    0.55
    USC
    0.55
    Activations Density 27.312%

    No Known Activations