© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15984
    Prev
    Next
    INDEX
    Explanations

    the word "the" or similar articles

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    lorette
    -0.64
     Nowy
    -0.60
    سم
    -0.55
     useAuth
    -0.53
    pted
    -0.52
     "..\..\
    -0.51
     formel
    -0.51
    Witch
    -0.50
    witched
    -0.50
     skis
    -0.50
    POSITIVE LOGITS
    Personendaten
    0.83
     protoimpl
    0.63
     Signalez
    0.59
    makeConstraints
    0.59
    ыгана
    0.58
     boste
    0.54
    MessageOf
    0.53
     ویکی‌پدیا
    0.52
    simpleType
    0.51
    voyez
    0.51
    Activations Density 6.560%

    No Known Activations