© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14585
    Prev
    Next
    INDEX
    Explanations

    capitalized words, words related to scrapbooking and the names of television programs

    oai_token-act-pair · gemini-2.0-flash

    crafting projects

    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
     vectorielles
    -0.62
     ögon
    -0.60
    Demografia
    -0.59
     disambigu
    -0.58
     vägen
    -0.58
     käytet
    -0.58
     håll
    -0.58
    RegressionTest
    -0.57
     artificiales
    -0.56
     virš
    -0.56
    POSITIVE LOGITS
     propOrder
    0.55
    ners
    0.53
     The
    0.52
     my
    0.52
     ‘
    0.51
    Well
    0.50
    ems
    0.49
     it
    0.49
    ers
    0.48
     the
    0.47
    Activations Density 5.800%

    No Known Activations