© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15127
    Prev
    Next
    INDEX
    Explanations

    the pronouns "we," "us," and "our."

    oai_token-act-pair · gemini-2.0-flash

    first-person plural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    bootstrapcdn
    -0.74
     للمعارف
    -0.73
    حياته
    -0.72
     resourceCulture
    -0.71
    jsxFileName
    -0.69
    حياتها
    -0.68
    GIVEREF
    -0.68
    NUMX
    -0.67
    UserScript
    -0.66
    zzleHttp
    -0.63
    POSITIVE LOGITS
     ourselves
    1.15
    We
    0.96
     we
    0.90
    Our
    0.88
     our
    0.87
    we
    0.81
     We
    0.77
     Our
    0.76
     我们
    0.74
    Abbiamo
    0.74
    Activations Density 0.962%

    No Known Activations