© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14140
    Prev
    Next
    INDEX
    Explanations

    uses of possessive pronouns such as "its" and "her"/ "his," as well as definite articles like "the".

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     a
    -0.58
    ,
    -0.57
     his
    -0.56
     générations
    -0.55
     its
    -0.55
     and
    -0.54
     femeninos
    -0.49
     an
    -0.49
     nenhuma
    -0.49
     your
    -0.48
    POSITIVE LOGITS
     myſelf
    1.03
    WebServlet
    1.02
    contentLoaded
    1.02
     Majefty
    0.94
    ſelf
    0.93
     ſta
    0.92
     purpoſe
    0.92
     ſche
    0.90
     ſtand
    0.90
     transfieras
    0.89
    Activations Density 9.294%

    No Known Activations