© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7982
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and reflexive pronouns

    oai_token-act-pair · gemini-2.0-flash

    ourselves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    setVerticalGroup
    -0.99
    }{*}{}
    -0.92
     disambiguazione
    -0.92
     beginnetje
    -0.89
    Coordonnées
    -0.85
    Tikang
    -0.85
    complexType
    -0.83
    EndGlobalSection
    -0.83
    IUrlHelper
    -0.81
    XmlAccessType
    -0.80
    POSITIVE LOGITS
     volna
    0.56
     doveva
    0.56
     upon
    0.56
     çerçe
    0.56
     (‘
    0.55
    <eos>
    0.55
    er
    0.54
    t
    0.53
    we
    0.53
    自分は
    0.52
    Activations Density 0.961%

    No Known Activations