© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15278
    Prev
    Next
    INDEX
    Explanations

    the words "can" and "to" and the pronoun "you"

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     can
    -0.48
     being
    -0.46
     Be
    -0.44
     
    -0.43
    uais
    -0.41
    ToBe
    -0.41
    Be
    -0.39
     boleh
    -0.39
     be
    -0.38
    marvin
    -0.38
    POSITIVE LOGITS
    OGND
    1.02
     незавершена
    0.98
    AndEndTag
    0.96
    setVerticalGroup
    0.95
    ]")]
    0.89
    :✨
    0.87
     betweenstory
    0.86
    новниш
    0.86
     utafitiHapana
    0.84
    ագրություններ
    0.83
    Activations Density 1.888%

    No Known Activations