© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13552
    Prev
    Next
    INDEX
    Explanations

    words related to legal, scientific or artistic texts, or some turning point in these endeavors.

    oai_token-act-pair · gemini-2.0-flash

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     préalable
    -0.73
     vooraf
    -0.65
     anteced
    -0.62
    DebuggerNonUser
    -0.62
     previamente
    -0.60
     متعلقه
    -0.60
    تقاوى
    -0.59
    PropertyChanging
    -0.59
     previo
    -0.58
     trước
    -0.56
    POSITIVE LOGITS
    EndProject
    0.67
     onPostExecute
    0.65
     later
    0.61
     ffilmiau
    0.59
    Sucesor
    0.57
     afterwards
    0.57
     الحره
    0.56
    StoryboardSegue
    0.55
     späteren
    0.54
     subsequent
    0.52
    Activations Density 2.567%

    No Known Activations