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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3093
    Prev
    Next
    INDEX
    Explanations

    text referring to the possessive first person plural (our, ours, we, us)

    oai_token-act-pair · gemini-2.0-flash

    our

    np_max-act-logits · gemini-2.0-flash
    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
     our
    -2.53
    Our
    -2.14
     Our
    -2.13
     OUR
    -1.83
    our
    -1.76
    我们的
    -1.70
     nosso
    -1.68
    我們的
    -1.65
     nossa
    -1.59
     unserer
    -1.57
    POSITIVE LOGITS
    ║
    0.52
    OpenHelper
    0.52
     personalities
    0.51
    のを
    0.50
    ClCompile
    0.50
    osh
    0.50
     Ababa
    0.49
    Comté
    0.49
    olog
    0.48
    ptid
    0.48
    Activations Density 1.767%

    No Known Activations