© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10431
    Prev
    Next
    INDEX
    Explanations

    the word "host" and its plural form, especially in the context of computing and networking

    oai_token-act-pair · gemini-2.0-flash

    host

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ^(@)
    -0.97
    ſelf
    -0.95
     myſelf
    -0.91
    хьтан
    -0.91
     Mémoires
    -0.89
     Roskov
    -0.88
     $_"
    -0.88
     reaſon
    -0.88
     pleaſure
    -0.86
     //$
    -0.85
    POSITIVE LOGITS
    ↵↵
    0.92
     
    0.81
     The
    0.73
     (
    0.66
     –
    0.65
    (
    0.65
    <eos>
    0.64
    -
    0.62
      
    0.60
    2
    0.60
    Activations Density 0.727%

    No Known Activations