© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 387
    Prev
    Next
    INDEX
    Explanations

    sentences using forms of the verb "to be."

    oai_token-act-pair · gemini-2.0-flash

    scientific studies/research

    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
    Negative Logits
     tartalomajánló
    -0.65
    CompleteListener
    -0.63
     Roskov
    -0.60
    UnusedPrivate
    -0.56
    __(/*!
    -0.55
    RSpec
    -0.53
    resave
    -0.52
    tableFuture
    -0.51
    ParallelGroup
    -0.49
     oprot
    -0.49
    POSITIVE LOGITS
     randomization
    0.54
    tioner
    0.53
    mmä
    0.52
     recrystal
    0.52
    :✨
    0.52
    retes
    0.51
    izos
    0.50
     Carmine
    0.48
    hofer
    0.48
     engraving
    0.48
    Activations Density 9.186%

    No Known Activations