© 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. 2824
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are subjective, that express feelings or opinions or reactions

    oai_token-act-pair · gemini-2.0-flash

    time references

    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
     gainera
    -0.47
     tæ
    -0.39
    ]<=
    -0.39
    hæng
    -0.38
    indu
    -0.37
    ոյ
    -0.37
    rowing
    -0.36
    шне
    -0.35
    까
    -0.35
    спо
    -0.35
    POSITIVE LOGITS
     today
    1.83
     tonight
    1.52
    today
    1.47
     nowadays
    1.34
     hoje
    1.30
     TODAY
    1.29
     сегодня
    1.29
     yesterday
    1.24
     Today
    1.22
     oggi
    1.21
    Activations Density 5.351%

    No Known Activations