© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10427
    Prev
    Next
    INDEX
    Explanations

    dates, titles, place names, and names of people/organizations

    oai_token-act-pair · gemini-2.0-flash

    Names and various topics

    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
     not
    -1.00
     enough
    -0.93
     something
    -0.87
     somehow
    -0.87
     necessarily
    -0.87
     maybe
    -0.86
     rather
    -0.85
     obvious
    -0.84
     sufficiently
    -0.83
     definitely
    -0.82
    POSITIVE LOGITS
     Normdatei
    0.49
     presented
    0.48
     published
    0.46
     inaugurated
    0.46
     attended
    0.45
     conducted
    0.42
     participated
    0.42
     publishes
    0.42
     presenta
    0.40
     hosted
    0.39
    Activations Density 18.019%

    No Known Activations