© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15077
    Prev
    Next
    INDEX
    Explanations

    sentences using the word "to" as an infinitive

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -0.69
    OGND
    -0.53
     assisti
    -0.52
     angefü
    -0.46
     isShow
    -0.46
     bestaat
    -0.45
     asisti
    -0.44
    delu
    -0.44
     kasarigan
    -0.44
    amily
    -0.44
    POSITIVE LOGITS
     EconPapers
    0.68
    Билгалдахарш
    0.65
    حياتها
    0.65
     seamlessly
    0.64
    Παραπομπές
    0.63
     peacefully
    0.62
     الحره
    0.59
    ++];
    0.59
    ---+
    0.59
     للمعارف
    0.57
    Activations Density 5.127%

    No Known Activations