© 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. 1130
    Prev
    Next
    INDEX
    Explanations

    code snippets containing Java keywords or database commands

    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_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
    styleType
    -0.80
     noDo
    -0.72
    UserScript
    -0.71
    PMailer
    -0.65
    IsContent
    -0.65
    awtextra
    -0.64
     يتيمه
    -0.64
    createCanvas
    -0.63
     ModelExpression
    -0.60
     MainAxisSize
    -0.60
    POSITIVE LOGITS
     compaction
    0.47
    topology
    0.46
     Kuz
    0.46
    InOrder
    0.46
    }{*}{
    0.45
     periodicity
    0.45
    arquía
    0.44
     ordem
    0.44
    archy
    0.44
    Executor
    0.43
    Activations Density 12.768%

    No Known Activations