© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10726
    Prev
    Next
    INDEX
    Explanations

    female pronouns and possessives

    oai_token-act-pair · gemini-2.0-flash

    her

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     she
    -1.96
    she
    -1.53
    She
    -1.48
     She
    -1.43
     wife
    -1.11
    彼女
    -1.02
     wives
    -0.99
     SHE
    -0.97
    她
    -0.96
     ela
    -0.96
    POSITIVE LOGITS
     he
    1.02
     он
    0.88
     him
    0.81
     él
    0.74
     ihn
    0.73
    ньому
    0.72
     ihm
    0.69
    他
    0.68
     він
    0.68
    VersionUID
    0.64
    Activations Density 1.383%

    No Known Activations