© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12476
    Prev
    Next
    INDEX
    Explanations

    terms related to cosmic lens observation and non-gaussian statistics

    oai_token-act-pair · gemini-2.0-flash

    galaxy simulations

    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
    AndEndTag
    -0.77
    RectangleBorder
    -0.71
    extAlignment
    -0.68
    IContainer
    -0.68
    AddTagHelper
    -0.66
    LLocation
    -0.65
     HttpNotFound
    -0.65
     Normdatei
    -0.65
    UIControlState
    -0.63
     transfieras
    -0.62
    POSITIVE LOGITS
     onCreateView
    0.54
     Kahn
    0.52
    Obrázky
    0.46
     Kaiser
    0.46
     peeling
    0.45
    مصادر
    0.45
    Kaiser
    0.45
    phic
    0.44
     HSC
    0.44
    phan
    0.44
    Activations Density 4.756%

    No Known Activations