© 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. 4596
    Prev
    Next
    INDEX
    Explanations

    text that introduces a scientific paper or blog post

    oai_token-act-pair · gemini-2.0-flash

    academic introductions

    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
     introduction
    -3.23
     introduce
    -2.97
     introduced
    -2.89
    introduction
    -2.81
     Introduction
    -2.81
     Introduce
    -2.77
     introductions
    -2.77
     introducing
    -2.77
     introdu
    -2.69
    introduced
    -2.67
    POSITIVE LOGITS
    AxisAlignment
    0.59
     useRouter
    0.56
    SuccessListener
    0.55
    ołnier
    0.54
    Atsauces
    0.54
    jewództ
    0.52
    readystatechange
    0.48
    NSError
    0.47
    CompoundButton
    0.47
    ngdoc
    0.46
    Activations Density 3.410%

    No Known Activations