© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9975
    Prev
    Next
    INDEX
    Explanations

    words or phrases in languages other than English and/or related to chemistry/medicine

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    \}\\
    -0.52
    okan
    -0.45
    dibles
    -0.43
    setDo
    -0.42
     Immer
    -0.41
    ẵn
    -0.41
     Grammar
    -0.40
    待
    -0.40
     сме
    -0.40
    viesa
    -0.40
    POSITIVE LOGITS
     насељу
    0.75
    principalTable
    0.73
    <bos>
    0.72
    RegressionTest
    0.71
     Infórmanos
    0.69
     poffible
    0.68
     متعلقه
    0.65
     '\\;'
    0.65
     éché
    0.63
     ſeveral
    0.63
    Activations Density 0.613%

    No Known Activations