© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11422
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people using pronouns like 'they' and 'we'

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs and pronouns

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

    They

    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
     their
    -1.17
    their
    -1.17
    Their
    -1.16
     Their
    -1.06
     thier
    -0.91
     kanilang
    -0.89
    他们的
    -0.89
     THEIR
    -0.88
    他們的
    -0.86
     leur
    -0.84
    POSITIVE LOGITS
     are
    1.16
     have
    0.85
     aren
    0.85
     were
    0.79
     don
    0.76
     want
    0.74
     know
    0.73
     introduce
    0.73
     join
    0.71
     come
    0.70
    Activations Density 1.892%

    No Known Activations