© 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. 12476
    Prev
    Next
    INDEX
    Explanations

    mentions of feelings, mental state, or emotion, especially in medical contexts

    oai_token-act-pair · gemini-2.0-flash

    emotional

    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
    MigrationBuilder
    -0.91
    CodeAttribute
    -0.87
    RegressionTest
    -0.86
    makeConstraints
    -0.81
    SOUNDBITE
    -0.80
    참고
    -0.80
    KommentareTeilen
    -0.78
    Hozzáférés
    -0.77
    ⓧ
    -0.77
    ագրություններ
    -0.76
    POSITIVE LOGITS
     themſelves
    0.64
     Monfieur
    0.60
    Contactez
    0.60
    nhung
    0.58
    jusqu
    0.58
     Theſe
    0.58
     itſelf
    0.55
    OTROS
    0.55
    équences
    0.55
     Longueur
    0.55
    Activations Density 2.121%

    No Known Activations