© 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. 12618
    Prev
    Next
    INDEX
    Explanations

    sentences related to sports leagues or organizations

    oai_token-act-pair · gemini-2.0-flash

    terms related to male gender

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

    male

    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
     women
    -1.16
     woman
    -1.08
     Women
    -0.99
    women
    -0.97
    Women
    -0.96
    woman
    -0.95
     Woman
    -0.91
     WOMEN
    -0.85
    Woman
    -0.84
    WOMEN
    -0.82
    POSITIVE LOGITS
     boy
    1.39
     boys
    1.38
     male
    1.38
    boy
    1.27
    boys
    1.26
    male
    1.22
     Boys
    1.21
    BOYS
    1.21
    Boys
    1.21
    Boy
    1.19
    Activations Density 1.150%

    No Known Activations