© 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. 7302
    Prev
    Next
    INDEX
    Explanations

    what appear to be article titles, especially including years and hyphens

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act-logits · gemini-2.0-flash

    opening punctuation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    rachtet
    -0.56
     himo
    -0.55
    :✨
    -0.54
     propOrder
    -0.54
     gezicht
    -0.54
     ویکی‌پدی
    -0.54
     solches
    -0.53
     hindurch
    -0.53
    mergeFrom
    -0.52
    verhältnisse
    -0.52
    POSITIVE LOGITS
    Nieder
    0.62
    Stadt
    0.61
    Liebe
    0.60
    Köln
    0.60
    Feuer
    0.60
    Nein
    0.59
    Neue
    0.59
    Danke
    0.59
    München
    0.59
    danke
    0.59
    Activations Density 24.832%

    No Known Activations