© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4250
    Prev
    Next
    INDEX
    Explanations

    words related to technical topics

    oai_token-act-pair · gemini-2.0-flash

    patience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    /
    -0.44
     individuelle
    -0.42
     D
    -0.41
    AndEndTag
    -0.41
    uxxxx
    -0.41
     procedure
    -0.40
     N
    -0.40
    이버
    -0.39
     individual
    -0.39
     usually
    -0.39
    POSITIVE LOGITS
     AssemblyCompany
    0.88
     Monfieur
    0.77
     myſelf
    0.76
    :✨
    0.73
    ValueStyle
    0.73
     Anſ
    0.73
     كومونز
    0.72
     Houſe
    0.69
    TestingModule
    0.69
    IsContent
    0.68
    Activations Density 20.193%

    No Known Activations