© 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. 14308
    Prev
    Next
    INDEX
    Explanations

    phrases describing people or states of being with a somewhat negative or disadvantaged connotation.

    oai_token-act-pair · gemini-2.0-flash

    words indicating companionship or camaraderie

    np_token-act-pair-logits · gpt-4o-mini

    fellow

    np_max-act-logits · gemini-2.0-flash
    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
     resourceCulture
    -0.79
    Datuak
    -0.77
    RTLR
    -0.73
     estekak
    -0.71
     nakalista
    -0.69
    PRNewswire
    -0.66
    UnusedPrivate
    -0.66
    swire
    -0.65
     AssemblyCulture
    -0.65
    Hentet
    -0.65
    POSITIVE LOGITS
     fellow
    1.34
     fellows
    1.01
    Fellow
    1.00
    fellow
    0.98
     Fellow
    0.96
     FELLOW
    0.91
     chap
    0.85
     Fellows
    0.74
     fella
    0.71
    chap
    0.65
    Activations Density 0.999%

    No Known Activations