© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2460
    Prev
    Next
    INDEX
    Explanations

    words regarding emotions, feelings, and health

    oai_token-act-pair · gemini-2.0-flash

    happy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -2.63
     Happy
    -2.58
    Happy
    -2.47
    happy
    -2.36
     HAPPY
    -2.28
    HAPPY
    -2.19
     happiest
    -2.09
     happiness
    -2.00
     happier
    -1.99
     satisfied
    -1.97
    POSITIVE LOGITS
    ::$_
    0.49
    oweit
    0.43
    额
    0.43
    हाँ
    0.42
    ecera
    0.40
    dymyr
    0.40
     posthum
    0.40
    guia
    0.39
    AnchorStyles
    0.39
    witness
    0.38
    Activations Density 1.844%

    No Known Activations