© 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. 12125
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to official legal cases, scientific studies, software development and baby care, with words ending in '-ed'.

    oai_token-act-pair · gemini-2.0-flash

    Legal and internet text fragments

    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
    DockStyle
    -0.81
     pinulongan
    -0.72
     Roskov
    -0.70
    دانشنامهٔ
    -0.70
    Geplaatst
    -0.69
     defaultstate
    -0.69
    Brainz
    -0.67
    AccessorTable
    -0.67
     revanche
    -0.66
     ExecuteAsync
    -0.66
    POSITIVE LOGITS
    المشاركات
    0.48
    laris
    0.46
     ännu
    0.44
    TagMode
    0.42
    jà
    0.41
    Er
    0.40
    precious
    0.39
     مقدس
    0.39
     där
    0.39
     Er
    0.38
    Activations Density 3.116%

    No Known Activations