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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10515
    Prev
    Next
    INDEX
    Explanations

    java code syntax, especially the keywords 'new', 'class', assignment operators, generic types, the 'Scanner' type, and method calls

    oai_token-act-pair · gemini-2.0-flash

    new

    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
     automatically
    -0.59
     ===
    -0.52
     is
    -0.50
     contains
    -0.50
    })));
    -0.49
    ":{"
    -0.48
     within
    -0.48
     on
    -0.48
    /=
    -0.48
     ==
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.91
     typelib
    0.85
     MenuView
    0.80
     ModelExpression
    0.78
    AndEndTag
    0.75
    SharedCtor
    0.75
    sizeCache
    0.71
    ReusableCell
    0.70
    Geplaatst
    0.69
    ftagPool
    0.68
    Activations Density 3.962%

    No Known Activations