© 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. 13281
    Prev
    Next
    INDEX
    Explanations

    a variety of content, including names of organizations, times etc

    oai_token-act-pair · gemini-2.0-flash

    ' and 1

    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
     itſelf
    -0.65
     himſelf
    -0.65
     Efq
    -0.59
    PERATURE
    -0.58
    tôi
    -0.55
     themſelves
    -0.55
    nastics
    -0.54
    Czytaj
    -0.54
     myſelf
    -0.54
    UAGE
    -0.53
    POSITIVE LOGITS
    RegressionTest
    0.56
     Tri
    0.48
    Ti
    0.44
     Tre
    0.44
    MetaType
    0.42
     Es
    0.41
     Ve
    0.41
    CppMethod
    0.40
     En
    0.40
     Sol
    0.40
    Activations Density 22.406%

    No Known Activations