© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14051
    Prev
    Next
    INDEX
    Explanations

    references to time periods, especially the early 1900s, 2000s, and 2010s, as well as words related to news and societal order.

    oai_token-act-pair · gemini-2.0-flash

    early or late

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     more
    -0.46
     nonatomic
    -0.44
    nt
    -0.43
    런
    -0.41
     dasarnya
    -0.41
    nonatomic
    -0.40
     way
    -0.40
     an
    -0.40
    tt
    -0.39
    t
    -0.39
    POSITIVE LOGITS
    astéroïdes
    0.72
     utafitiHapana
    0.69
    BeginContext
    0.69
    GroupLayout
    0.68
    Дереккөздер
    0.68
     AssemblyCulture
    0.67
     Samaria
    0.67
     FishBase
    0.67
    BufferException
    0.66
     betweenstory
    0.66
    Activations Density 10.333%

    No Known Activations