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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11535
    Prev
    Next
    INDEX
    Explanations

    frequent short words that often appear in legal documents

    oai_token-act-pair · gemini-2.0-flash

    the/same

    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
    xase
    -0.53
    GeneratedCode
    -0.51
     colorés
    -0.50
    interopRequire
    -0.50
    rfloor
    -0.49
     coloré
    -0.48
    gridLayout
    -0.48
     larmes
    -0.47
    tuce
    -0.46
    styleable
    -0.46
    POSITIVE LOGITS
    сылкі
    0.82
     surla
    0.75
    DockStyle
    0.70
    SharedCtor
    0.63
    WithIOException
    0.60
     Members
    0.58
     betweenstory
    0.57
    RenderAtEndOf
    0.56
    Abp
    0.56
     مشين
    0.54
    Activations Density 7.883%

    No Known Activations