© 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. 13468
    Prev
    Next
    INDEX
    Explanations

    words involved in arguments and financial difficulties.

    oai_token-act-pair · gemini-2.0-flash

    problems and effort

    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
     NSError
    -0.55
     otomatig
    -0.54
     Roskov
    -0.53
    addCriterion
    -0.52
     burden
    -0.52
     ὁ
    -0.51
     cost
    -0.51
    ůli
    -0.50
     loss
    -0.49
    ちな
    -0.49
    POSITIVE LOGITS
    UserScript
    0.63
    Xna
    0.58
     bonuses
    0.57
     estimés
    0.56
    icoot
    0.56
     spite
    0.52
    最快更新
    0.52
    boost
    0.52
     tươi
    0.51
    CURLOPT
    0.51
    Activations Density 13.892%

    No Known Activations