© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11250
    Prev
    Next
    INDEX
    Explanations

    instances of the words "you", "they", or "if"

    oai_token-act-pair · gemini-2.0-flash

    don/doesn

    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
     nie
    -0.97
     bukan
    -0.85
     wasnt
    -0.83
    Enllaces
    -0.82
    NotBe
    -0.81
     Bukan
    -0.80
     Not
    -0.79
     not
    -0.79
    Bukan
    -0.77
    Not
    -0.73
    POSITIVE LOGITS
     don
    0.96
    don
    0.81
    Don
    0.78
     doesn
    0.77
     Don
    0.72
     DON
    0.68
     didn
    0.67
    DON
    0.67
     shouldn
    0.66
    doesn
    0.64
    Activations Density 1.494%

    No Known Activations