© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12447
    Prev
    Next
    INDEX
    Explanations

    the word "overall" and relate it to numbers, sizes, breadth and a general negativity

    oai_token-act-pair · gemini-2.0-flash

    whole/overall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Efq
    -0.90
     Jefus
    -0.75
     Majefty
    -0.74
     للمعارف
    -0.73
     houſe
    -0.71
     faſt
    -0.70
     Monfieur
    -0.70
    клопе
    -0.69
    Geplaatst
    -0.69
     photolibrary
    -0.69
    POSITIVE LOGITS
    webElementXpaths
    0.53
    sizeCache
    0.46
     bản
    0.43
     but
    0.42
     mergeFrom
    0.41
     hoeft
    0.41
    kret
    0.40
     giả
    0.40
     inferior
    0.40
    unik
    0.40
    Activations Density 1.035%

    No Known Activations