© 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. 12994
    Prev
    Next
    INDEX
    Explanations

    the word "happy" (and sometimes words with similar meanings).

    oai_token-act-pair · gemini-2.0-flash

    happy

    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
     happy
    -2.42
    happy
    -2.11
     Happy
    -2.09
    Happy
    -2.02
     HAPPY
    -1.77
    HAPPY
    -1.48
     heureux
    -1.43
     felices
    -1.30
     feliz
    -1.27
     happier
    -1.25
    POSITIVE LOGITS
    évaluateur
    0.88
     myſelf
    0.79
    NUMX
    0.78
     createSprite
    0.78
    SBATCH
    0.77
     GenerationType
    0.77
    WebElementEntity
    0.76
    IVEREF
    0.76
     ―――――
    0.74
    BrowserModule
    0.73
    Activations Density 1.075%

    No Known Activations