© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2897
    Prev
    Next
    INDEX
    Explanations

    the phrase "I was"

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating past actions or experiences

    np_token-act-pair-logits · gpt-4o-mini

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     تانيه
    -0.84
     Réponses
    -0.81
     للمعارف
    -0.81
    BagConstraints
    -0.80
    Enllaces
    -0.79
    InjectAttribute
    -0.79
    ValueStyle
    -0.76
     OMITBAD
    -0.75
    حياته
    -0.75
    ագրություններ
    -0.73
    POSITIVE LOGITS
     so
    0.59
     present
    0.54
     invited
    0.51
     watching
    0.47
     going
    0.46
     пото
    0.45
     born
    0.45
    akan
    0.45
     waiting
    0.45
     disappointed
    0.45
    Activations Density 1.120%

    No Known Activations