© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6236
    Prev
    Next
    INDEX
    Explanations

    the letter "t" when it follows the word "isn'" or "doesn'"

    oai_token-act-pair · gemini-2.0-flash

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    t
    -2.11
     t
    -1.45
    T
    -1.30
     T
    -1.16
     т
    -0.96
    ｔ
    -0.90
    Т
    -0.79
    𝑡
    -0.79
    т
    -0.79
    tC
    -0.79
    POSITIVE LOGITS
     not
    1.77
     Not
    1.19
     NOT
    1.09
    not
    1.02
    Not
    1.01
     bukan
    0.94
     nicht
    0.94
     tidak
    0.93
     niet
    0.93
     ikke
    0.92
    Activations Density 0.258%

    No Known Activations