© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11620
    Prev
    Next
    INDEX
    Explanations

    determiners, prepositions, and pronouns in the context of someone's personal or professional history/resume.

    oai_token-act-pair · gemini-2.0-flash

    people and occupation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    aimerais
    -0.45
    strando
    -0.43
     <=",
    -0.41
    GoogleApiClient
    -0.40
    twimg
    -0.39
    arXiv
    -0.38
     Pons
    -0.38
    BeforeClass
    -0.37
     Reverso
    -0.37
     syns
    -0.37
    POSITIVE LOGITS
    fjspx
    0.68
    AddTagHelper
    0.64
    PMailer
    0.63
    Diweddarwch
    0.61
     continúas
    0.60
     AppCompatTheme
    0.60
     initComponents
    0.60
    AddHtmlAttribute
    0.57
    цездатний
    0.57
     contextLoads
    0.56
    Activations Density 1.217%

    No Known Activations