© 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. 7296
    Prev
    Next
    INDEX
    Explanations

    text related to the persecution and deaths of minority groups during World War II.

    oai_token-act-pair · gemini-2.0-flash

    terms related to incarceration or imprisonment

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

    Holocaust

    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
     Shakspeare
    -0.75
    الإنجليزية
    -0.74
     Shaksp
    -0.73
    /*
    -0.68
    //
    -0.64
    новниш
    -0.64
     >=",
    -0.64
    itinéraire
    -0.59
    ChildScrollView
    -0.59
     Thine
    -0.59
    POSITIVE LOGITS
     jail
    0.53
    queryset
    0.50
     sür
    0.49
     concentration
    0.49
     prison
    0.48
    AttributeSet
    0.46
    gy
    0.46
     ом
    0.45
    ensus
    0.44
    ục
    0.44
    Activations Density 6.924%

    No Known Activations