© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11405
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to strong emotion or interpersonal conflict

    oai_token-act-pair · gemini-2.0-flash

    emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    новништво
    -0.69
    rungsseite
    -0.68
     שוליים
    -0.66
    httphttps
    -0.62
     ExecuteAsync
    -0.61
    DebuggerNonUser
    -0.61
    createServer
    -0.60
    __':
    -0.59
    SharedDtor
    -0.58
    dropna
    -0.56
    POSITIVE LOGITS
     surprise
    0.93
    surprise
    0.86
     delight
    0.81
     joy
    0.80
     excitement
    0.78
     disbelief
    0.78
     disappointment
    0.77
     shock
    0.77
     annoyance
    0.76
     pleasure
    0.76
    Activations Density 4.299%

    No Known Activations