© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10137
    Prev
    Next
    INDEX
    Explanations

    names of universities, cities, publications and other institutions.

    oai_token-act-pair · 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
    TypedDataSet
    -0.59
    SceneManagement
    -0.51
     "..\..\
    -0.49
    atimes
    -0.48
     становника
    -0.47
    AspNetCore
    -0.47
    Rüyada
    -0.46
    nehmung
    -0.45
    BASEPATH
    -0.45
    GenerationType
    -0.44
    POSITIVE LOGITS
    ]--;
    0.72
     nahilalakip
    0.59
    AsUp
    0.55
     Kans
    0.55
    الدراسه
    0.54
     !$
    0.53
     Shub
    0.53
    پیوند
    0.53
    ADELPHIA
    0.52
    }\]
    0.52
    Activations Density 0.813%

    No Known Activations