© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13099
    Prev
    Next
    INDEX
    Explanations

    mentions of the pronoun 'he', often in conjunction with auxiliary verbs or possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    He

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     on
    -0.84
    saying
    -0.75
    sharing
    -0.71
     sharing
    -0.68
     running
    -0.66
    -
    -0.66
    speaking
    -0.66
     of
    -0.65
    carrying
    -0.65
     calling
    -0.65
    POSITIVE LOGITS
     EconPapers
    0.60
    />";
    0.50
    <bos>
    0.47
     يتيمه
    0.47
    GeneratedMessage
    0.46
    ighed
    0.46
     Behold
    0.46
    llac
    0.46
    солю
    0.45
    <!--[
    0.45
    Activations Density 9.625%

    No Known Activations