© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs such as "be", "have", or "do"

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "at"

    np_token-act-pair-logits · gpt-4o-mini
    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
    BagLayout
    -0.66
    ReusableCell
    -0.63
    ISupport
    -0.61
     onPostExecute
    -0.58
     незавершена
    -0.58
    ########.
    -0.58
    anyahu
    -0.55
     noDo
    -0.55
     kasarigan
    -0.54
     оригіналу
    -0.54
    POSITIVE LOGITS
     at
    1.73
     last
    1.40
     At
    1.13
    At
    1.09
    last
    1.08
    at
    0.99
    Last
    0.96
     Last
    0.94
     LAST
    0.88
     dernier
    0.87
    Activations Density 1.217%

    No Known Activations