© 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. 4017
    Prev
    Next
    INDEX
    Explanations

    words relating to interpersonal relationships, especially those involving romantic or political conflict

    oai_token-act-pair · gemini-2.0-flash

    titles of female royalty or nobility

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

    female

    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
    تقاوى
    -0.72
     suaminya
    -0.68
     mannen
    -0.61
     Jej
    -0.60
     her
    -0.60
     Fathers
    -0.57
     fathers
    -0.56
     grandpa
    -0.56
     gentlemen
    -0.56
    对她
    -0.56
    POSITIVE LOGITS
     actress
    0.81
     Lady
    0.80
     lady
    0.77
     goddess
    0.75
     female
    0.75
     queen
    0.75
     Princess
    0.74
     girl
    0.74
     princess
    0.73
     Queen
    0.73
    Activations Density 1.961%

    No Known Activations