© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6355
    Prev
    Next
    INDEX
    Explanations

    context related to sports, pregnant women, or clothing

    oai_token-act-pair · gemini-2.0-flash

    terms related to women

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

    women

    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
     boys
    -1.40
     male
    -1.37
     boy
    -1.33
    Boys
    -1.27
    boy
    -1.25
    boys
    -1.25
     masculina
    -1.21
    BOYS
    -1.21
     males
    -1.20
    male
    -1.20
    POSITIVE LOGITS
     women
    1.37
     Women
    1.19
     woman
    1.18
    women
    1.15
    Women
    1.13
     Woman
    1.04
     WOMEN
    1.04
    woman
    1.03
    WOMEN
    0.96
     female
    0.92
    Activations Density 1.631%

    No Known Activations