© 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. 13398
    Prev
    Next
    INDEX
    Explanations

    isolated numbers and mathematical expressions.

    oai_token-act-pair · gemini-2.0-flash

    calculations

    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
    kust
    -0.46
     recursively
    -0.45
    indest
    -0.44
    äsident
    -0.43
     perak
    -0.42
    ContentAlignment
    -0.41
    Referencer
    -0.41
    latego
    -0.41
    Datuak
    -0.41
     plasti
    -0.40
    POSITIVE LOGITS
    évaluateur
    0.65
    webElementXpaths
    0.63
    fromnode
    0.61
     căr
    0.59
    rungsseite
    0.59
     EClass
    0.57
     indisponible
    0.57
    QMetaType
    0.57
     دیکھیے
    0.56
    RTSC
    0.56
    Activations Density 2.644%

    No Known Activations