© 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. 2060
    Prev
    Next
    INDEX
    Explanations

    the pronoun combinations "he/she" and "his/her."

    oai_token-act-pair · gemini-2.0-flash

    pronouns related to female references

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

    say "female pronoun"

    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
    Rujuakan
    -0.58
     Paglinawan
    -0.57
    enerys
    -0.51
    memoized
    -0.50
    InitVars
    -0.49
     stone
    -0.48
    ReLU
    -0.48
     III
    -0.46
    клопе
    -0.46
     na
    -0.46
    POSITIVE LOGITS
     herself
    1.11
     her
    1.08
     she
    0.97
     그녀
    0.86
     její
    0.84
    herself
    0.80
    حياتها
    0.78
     onAnimation
    0.78
     hennes
    0.77
    彼女の
    0.76
    Activations Density 0.747%

    No Known Activations