© 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. 9830
    Prev
    Next
    INDEX
    Explanations

    words related to the legal system, experiments, politeness and being on time.

    oai_token-act-pair · gemini-2.0-flash

    rare words

    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
     even
    -4.13
    even
    -3.81
    Even
    -3.47
     Even
    -3.44
     EVEN
    -3.31
    EVEN
    -2.92
     даже
    -2.92
     навіть
    -2.86
     incluso
    -2.78
     حتی
    -2.61
    POSITIVE LOGITS
    mergeFrom
    0.57
    mbggenerated
    0.57
    而已
    0.57
     distanciation
    0.55
    styleType
    0.54
     oprot
    0.54
     незавершена
    0.54
    ImageContext
    0.54
    Билгалдахарш
    0.53
    parsedMessage
    0.53
    Activations Density 8.904%

    No Known Activations