© 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. 15215
    Prev
    Next
    INDEX
    Explanations

    the word "block" associated with various terms

    oai_token-act-pair · gemini-2.0-flash

    block

    np_max-act-logits · gemini-2.0-flash

    instances of the word "block"

    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
    initializeApp
    -0.63
    UnitTesting
    -0.55
    NoSuchAlgorithm
    -0.55
     समीक्षाएं
    -0.53
    AddTagHelper
    -0.52
    tagHelper
    -0.49
    cartItems
    -0.49
    PasswordEncoder
    -0.47
    bufio
    -0.47
     Fermi
    -0.47
    POSITIVE LOGITS
     []),
    0.52
     Muñoz
    0.52
    }{*}{
    0.51
     {}),
    0.51
    holtz
    0.50
    ()',
    0.49
    >({
    0.49
    Jana
    0.49
     ''),
    0.49
     Mous
    0.49
    Activations Density 1.724%

    No Known Activations