© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9185
    Prev
    Next
    INDEX
    Explanations

    the pronoun "he" and its related forms, sometimes near time-related words and other pronouns.

    oai_token-act-pair · gemini-2.0-flash

    Narrative

    np_max-act-logits · gemini-2.0-flash

    pronouns Method used: 1 — because top tokens are subject pronouns — pronouns

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     could
    -1.45
     Could
    -1.40
    could
    -1.39
    Could
    -1.38
     könnten
    -1.03
     pourraient
    -0.97
     COULD
    -0.93
     kunne
    -0.90
     podrían
    -0.89
    podr
    -0.88
    POSITIVE LOGITS
     may
    0.96
     May
    0.79
    May
    0.74
    may
    0.70
     MAY
    0.67
    MAY
    0.57
    idopsis
    0.54
    likon
    0.54
    DIPSETTING
    0.52
    kloped
    0.50
    Activations Density 2.600%

    No Known Activations