© 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. 6216
    Prev
    Next
    INDEX
    Explanations

    references to a specific person, often using pronouns or names

    oai_token-act-pair · gemini-2.0-flash

    German possessive pronouns

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

    Pronouns and descriptions

    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
     his
    -2.91
     himself
    -2.88
    his
    -2.52
    himself
    -2.50
    彼の
    -2.09
    His
    -1.99
    彼は
    -1.95
     Himself
    -1.89
    彼が
    -1.88
     그의
    -1.80
    POSITIVE LOGITS
     ihrer
    0.78
     ihrem
    0.72
     &=&
    0.70
     ihren
    0.69
     ihre
    0.68
     their
    0.63
    &=&
    0.60
     Jej
    0.58
    &=&\
    0.56
     ihres
    0.56
    Activations Density 7.001%

    No Known Activations