© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1361
    Prev
    Next
    INDEX
    Explanations

    the phrase "with an eyeroll"

    oai_token-act-pair · gemini-2.0-flash

    emoticons and emoji

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     архивлан
    -0.56
     FishBase
    -0.54
     protoimpl
    -0.52
     EconPapers
    -0.52
    resave
    -0.50
    )։
    -0.49
     beginnetje
    -0.48
    Referències
    -0.48
    "]);
    -0.48
    "]="
    -0.48
    POSITIVE LOGITS
     emo
    1.06
     Emo
    0.85
    emo
    0.79
    Emo
    0.78
     emoji
    0.73
     emoticon
    0.70
     crying
    0.70
     Emoji
    0.69
     Reaction
    0.69
     emotion
    0.69
    Activations Density 1.364%

    No Known Activations