© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9254
    Prev
    Next
    INDEX
    Explanations

    words related to questions and reasoning, particularly "why," "what," and "how," as well as auxiliary verbs associated with them.

    oai_token-act-pair · gemini-2.0-flash

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     jsPsych
    -0.50
    elor
    -0.50
    expliquer
    -0.49
    urator
    -0.48
     perche
    -0.47
     Commande
    -0.47
    CompleteListener
    -0.47
     nominations
    -0.46
     Bondi
    -0.46
    Rujuakan
    -0.45
    POSITIVE LOGITS
    vokat
    0.54
     المعيارى
    0.52
    jaciół
    0.50
    islative
    0.49
    bleau
    0.48
     وتسجيلات
    0.48
    corder
    0.48
    resizingMask
    0.48
    abinieri
    0.47
    đèn
    0.47
    Activations Density 2.823%

    No Known Activations