© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11472
    Prev
    Next
    INDEX
    Explanations

    the suffix ".com" in domain names

    oai_token-act-pair · gemini-2.0-flash

    com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    com
    -2.83
    Com
    -1.99
     com
    -1.91
    COM
    -1.86
     Com
    -1.70
    coms
    -1.45
     COM
    -1.20
    comm
    -1.20
    COMM
    -1.09
     comm
    -1.07
    POSITIVE LOGITS
     userSchema
    0.58
    Respectfully
    0.56
    ContentAsync
    0.54
    complexType
    0.53
     оригіналу
    0.52
     ViewModel
    0.52
     getIs
    0.51
    
    0.51
    CreateModel
    0.50
    CPtr
    0.50
    Activations Density 0.844%

    No Known Activations