© 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. 11320
    Prev
    Next
    INDEX
    Explanations

    animal related health problems and the word sequence "is component selected".

    oai_token-act-pair · gemini-2.0-flash

    Unstructured/diverse text

    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
     “
    -3.66
     "
    -3.00
     ‘
    -2.72
    “
    -2.66
     „
    -2.55
     ‘‘
    -2.38
    「
    -2.36
    ，“
    -2.28
     «
    -2.27
     ”
    -2.23
    POSITIVE LOGITS
     nahilalakip
    0.69
    انجليز
    0.65
    €¦
    0.61
     kasarigan
    0.61
    __':
    0.60
    twimg
    0.57
    WebVitals
    0.56
     Wikimedijinoj
    0.55
    '],
    0.52
    __':
    0.52
    Activations Density 6.262%

    No Known Activations