© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10882
    Prev
    Next
    INDEX
    Explanations

    words about abstract concepts, often associated with current events or opinions

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Rohy
    -0.68
     aéreas
    -0.57
     engraçadas
    -0.56
    #
    -0.54
     femininas
    -0.54
     Italij
    -0.53
     dieux
    -0.52
     siihen
    -0.52
    lgari
    -0.51
     tekem
    -0.49
    POSITIVE LOGITS
     of
    2.81
     Of
    1.77
    of
    1.73
    Of
    1.67
     OF
    1.64
     của
    1.34
     ofthe
    1.17
    ofthe
    1.16
    ของ
    1.16
    OF
    1.15
    Activations Density 8.014%

    No Known Activations