© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3830
    Prev
    Next
    INDEX
    Explanations

    second person and first person pronouns, especially in colloquial usage

    oai_token-act-pair · gemini-2.0-flash

    Expressing wants or desires

    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
     wishes
    -1.30
     Wishes
    -1.26
     Wish
    -1.23
     wishing
    -1.20
     wished
    -1.17
    ^(@)
    -1.16
     wish
    -1.16
    Wish
    -1.13
     WISH
    -1.07
    wish
    -1.06
    POSITIVE LOGITS
     w
    0.49
     need
    0.48
     want
    0.46
    lar
    0.40
     just
    0.39
     en
    0.38
     what
    0.38
     ve
    0.38
     at
    0.37
    appar
    0.37
    Activations Density 2.308%

    No Known Activations