© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5752
    Prev
    Next
    INDEX
    Explanations

    sentences where a possibility or capability is being discussed. That is, it finds sentences with "can" and "be"

    oai_token-act-pair · gemini-2.0-flash

    Frustration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ichio
    -0.60
    eleste
    -0.54
     Rec
    -0.51
     गुण
    -0.50
    wär
    -0.50
    illo
    -0.49
    vician
    -0.48
    icity
    -0.45
    uni
    -0.44
    unna
    -0.44
    POSITIVE LOGITS
     frustrating
    1.05
     frust
    0.95
    frust
    0.93
     frustration
    0.90
     overwhelming
    0.85
     frustrated
    0.83
     frustrate
    0.83
     frustrations
    0.81
     frustra
    0.81
     Frust
    0.81
    Activations Density 0.828%

    No Known Activations