© 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. 8205
    Prev
    Next
    INDEX
    Explanations

    the word "keep" or "keeping" followed by a preposition

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "keep"

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

    keep

    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
     noqa
    -0.59
    KommentareTeilen
    -0.58
     intptr
    -0.50
     Geraadpleegd
    -0.48
    nasel
    -0.45
    úcar
    -0.44
    ագրություններ
    -0.42
    IM
    -0.42
    D
    -0.42
     estekak
    -0.41
    POSITIVE LOGITS
    </tfoot>
    0.67
     myſelf
    0.66
    agisse
    0.63
     theſe
    0.60
     alight
    0.59
    tralight
    0.58
    UpInside
    0.57
    mmate
    0.57
    ResumeLayout
    0.56
    ThroughAttribute
    0.56
    Activations Density 0.894%

    No Known Activations