© 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. 4914
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to warnings and instructions

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     amis
    -0.49
     Ananda
    -0.44
    critto
    -0.44
    acijos
    -0.44
    ptid
    -0.44
     Anarchy
    -0.43
     Democrá
    -0.43
     pran
    -0.43
     Ruz
    -0.43
    ritic
    -0.42
    POSITIVE LOGITS
    Sucesor
    0.72
    发表于
    0.68
     Make
    0.67
     cherchés
    0.66
     calendriers
    0.60
    󠁴
    0.60
     للمعارف
    0.59
    
    0.59
     Care
    0.59
     Hold
    0.57
    Activations Density 9.356%

    No Known Activations