© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8800
    Prev
    Next
    INDEX
    Explanations

    words or phrases expressing positive feelings, pride, or determination.

    oai_token-act-pair · gemini-2.0-flash

    words conveying empowerment and pride

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     nahilalakip
    -0.86
     EconPapers
    -0.80
     صوتيه
    -0.79
     protoimpl
    -0.73
    SharedDtor
    -0.67
    Diwedd
    -0.66
    хьтан
    -0.66
    AutoScaleMode
    -0.66
    findpost
    -0.65
    thâu
    -0.64
    POSITIVE LOGITS
    LOAT
    0.50
     simply
    0.49
     just
    0.49
    несе
    0.47
     Atkinson
    0.47
    gü
    0.46
    roma
    0.46
    oug
    0.42
    holi
    0.42
    tip
    0.41
    Activations Density 1.230%

    No Known Activations