© 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. 9376
    Prev
    Next
    INDEX
    Explanations

    questions asking if something is possible or if a thing exists

    oai_token-act-pair · gemini-2.0-flash

    the word "there"

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

    is

    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
    endphp
    -0.52
    지를
    -0.50
    вість
    -0.49
    tonsoft
    -0.49
     olivat
    -0.48
    وانید
    -0.47
    Jäh
    -0.47
     Obtén
    -0.47
    liau
    -0.46
    Gemeinden
    -0.46
    POSITIVE LOGITS
     there
    3.33
    there
    2.69
     THERE
    2.42
    There
    2.31
     There
    2.28
    THERE
    2.05
     هناك
    1.56
     theres
    1.51
    theres
    1.39
     thither
    1.34
    Activations Density 3.025%

    No Known Activations