© 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. 13797
    Prev
    Next
    INDEX
    Explanations

    phrases that follow a comma and include "so" or "you"

    oai_token-act-pair · gemini-2.0-flash

    the word "there"

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

    there

    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
     keiner
    -0.58
    &__
    -0.52
    PreferredItem
    -0.48
     without
    -0.47
    ものを
    -0.47
     neither
    -0.46
    ẫu
    -0.46
     ilman
    -0.45
     niente
    -0.45
    ImageField
    -0.45
    POSITIVE LOGITS
     there
    3.09
    there
    2.56
     THERE
    2.33
     There
    2.25
    There
    2.25
    THERE
    2.03
     هناك
    1.62
     theres
    1.49
    theres
    1.47
     thither
    1.22
    Activations Density 2.488%

    No Known Activations