© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4944
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating excess amounts or deviations from a norm.

    oai_token-act-pair · gemini-2.0-flash

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     unnecessary
    -1.38
     unreasonable
    -1.34
     inappropriate
    -1.31
     unwarranted
    -1.31
     unjustified
    -1.27
     incorrect
    -1.23
     unnecessarily
    -1.20
     inneces
    -1.20
     excessive
    -1.18
     unwanted
    -1.16
    POSITIVE LOGITS
    Autoritní
    0.57
     चीज़ों
    0.48
    InputTagHelper
    0.48
    TagHelper
    0.47
    findpost
    0.47
    uxxxx
    0.47
    omla
    0.47
    msgTypes
    0.45
    出版年
    0.45
     ProtoMessage
    0.45
    Activations Density 2.081%

    No Known Activations