© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6187
    Prev
    Next
    INDEX
    Explanations

    the word "validation" (and related words like "validates" or "validator")

    oai_token-act-pair · gemini-2.0-flash

    validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -1.19
     a
    -0.90
     in
    -0.85
     
    -0.82
     an
    -0.78
     (
    -0.75
     as
    -0.74
    ↵
    -0.73
     to
    -0.72
     at
    -0.70
    POSITIVE LOGITS
     Jefus
    1.52
     houſe
    1.48
     Majefty
    1.47
     Efq
    1.44
     Houſe
    1.43
     Chriftian
    1.38
     Shakspeare
    1.37
     myſelf
    1.34
     purpoſe
    1.34
     ſche
    1.34
    Activations Density 1.668%

    No Known Activations