© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8054
    Prev
    Next
    INDEX
    Explanations

    parts of Java code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ])))
    -0.45
     \\[
    -0.45
    LayoutPanel
    -0.44
     tilla
    -0.44
     machine
    -0.43
    ])):
    -0.43
    aut
    -0.42
    неопр
    -0.42
    pushFollow
    -0.42
     red
    -0.41
    POSITIVE LOGITS
    AddTagHelper
    0.88
     CreateTagHelper
    0.85
    Хьажоргаш
    0.77
    RectangleBorder
    0.73
     obſ
    0.73
     occaf
    0.72
     uſed
    0.69
     ſhall
    0.68
     faſt
    0.68
     purpoſe
    0.68
    Activations Density 0.094%

    No Known Activations