© 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. 14769
    Prev
    Next
    INDEX
    Explanations

    the word "really" and some words that often come near it

    oai_token-act-pair · gemini-2.0-flash

    really

    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
     really
    -1.02
    really
    -0.96
     Really
    -0.80
    Really
    -0.75
     wirklich
    -0.73
     vraiment
    -0.72
     realmente
    -0.71
     veramente
    -0.68
     davvero
    -0.68
     truly
    -0.67
    POSITIVE LOGITS
     resourceCulture
    1.23
     مشين
    0.93
    :✨
    0.90
    ArgsConstructor
    0.89
    CodedInputStream
    0.87
    UIControlState
    0.85
    NameInMap
    0.82
    SourceChecksum
    0.82
    parsedMessage
    0.82
    UnusedPrivate
    0.81
    Activations Density 2.661%

    No Known Activations