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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12358
    Prev
    Next
    INDEX
    Explanations

    instances of "he/she" along with surrounding pronouns and verbs.

    oai_token-act-pair · gemini-2.0-flash

    pronouns referring to females

    np_token-act-pair-logits · gpt-4o-mini
    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
    CloseOperation
    -0.97
    ньому
    -0.86
     him
    -0.84
    彼は
    -0.77
     okuyayım
    -0.75
     esso
    -0.74
     raiſ
    -0.71
    JspWriter
    -0.71
    istoitu
    -0.71
     usarlo
    -0.70
    POSITIVE LOGITS
     she
    3.28
     her
    3.02
    she
    2.56
    She
    2.31
     그녀
    2.27
     hers
    2.23
    彼女の
    2.16
    她
    2.06
    her
    2.03
     She
    2.02
    Activations Density 8.945%

    No Known Activations